Special Topics in Kernels, RL, Reward Hacking in Agents — Daniel Han, Unsloth

Hello everyone. Um yeah, thanks so much for coming today. Much appreciated. Um

yes, I'm Daniel. I'm from Anslaf. My

brother is also here today. Um but yeah, like you know, thanks for coming. Um,

so for you folks who don't know us, um, so we actually, you know, we're one of the largest distributors of language models and diffusion models as well. So

we don't just do language models. We

upload our models to hugging face. Um,

and you know, we're on the I think we're number 10 or something on the Oh, no, I don't I don't remember. But anyways,

we're on the list of the top organizations on Hugging Face. Um, we

have over 300 million total downloads.

Um, so definitely check us out on that.

Um you can run like you know Deepseek, GLM, many other models and we quantize them down using dynamic quantization. Um

so you can run them on your local computer.

Um we also do many bug fixes for open source models. Um so you know we you

source models. Um so you know we you know fix many bugs in you know OpenAI's GPUs um you know Meta's models um Google's models deepseas many other models we fix bugs in them. Um and so

like you know they have many issues sometimes and then we post about them on Twitter. um you know we post about our

Twitter. um you know we post about our findings um so you know m most of the open source models that you probably guys have used um are most likely fixed by us um and yeah like we collaborate

with everyone in the entire world um on you know model releases um yeah we also collaborate with hardware providers and you know we really appreciate the collaborations with everyone

we also don't just do model fixes and bug you know bugs we also introduce new features and we also like you know do fixes for the entire trading stack. Um

for example, we introduced something called async gradient checkpointing which is used by many organizations. Um

we also introduced flex attention which is used by many folks. Um and we also fixed a gradient accumulation bug fix um which increased accuracy by 1 to 3% um across the entire training stack. Um so

we don't just like you know do bug fixes for models um it's also like you know whole training stack um fixes and stuff like that.

So today, you know, the workshop is quite long. Um, so there will be

quite long. Um, so there will be multiple sections in the workshop. Um,

and so after each section, anyone can ask a question. Um, and so, you know, please, I guess, if I'm not sure if there's a microphone, but if you could raise your voice and you ask a question, you know, I'm more than happy to answer

them. Um, but you know, the first

them. Um, but you know, the first section we're going to be talking about is the state of AI. So, where is currently language models, AI models, where are they at currently? Um

so I'm not sure if everyone knows the meter plot. Um so this meter plot shows

meter plot. Um so this meter plot shows the time horizon of uh models. Um if you can you know every single task if it takes a human 16 hours can a model you

know finish that task. Um and you can see on this plot you know cloud mythos you know preview is very good. It can do tasks that humans can do that take you

know human 16 hours. Um you know opus 4.6 is also there. you know all the other models are also there and so you know this plot is very good because it symbolizes the AI models are getting

better and better and better over time you know recently with the launch of you know GPD 5.6 um you know just well their preview model um you know just on Friday um you

know I put the plot so they didn't so me didn't actually update their plot um because they said that the results were not trustworthy enough um but you know I just put it on the plot um and so you

can see that GBD 5.6 you know is around you know opus 4.6 sixth level I guess with large confidence bounds um so it's very you know uncertain about the

capabilities of the model um however if you include cheating so if you include that the model sometimes likes to cheat on some of the tasks then it actually goes to 270 hours um so we're directly

and you know if you look at the y-axis I actually did a disjoint graph um so the y-axis is 50 hours skipped to 250 hours um so if you can imagine the graph is

actually very skewed Um when I like made the graph, um GBD 5.6 was like a very big outlier. Um so I had to like

big outlier. Um so I had to like compress the graph. Um but this only you know this graph only works if you consider that GBD 5.6 cheated on some of the tasks. Um and so we'll be talking

the tasks. Um and so we'll be talking about you know why AI models cheat and how do we like you know solve these issues. Um but yeah this plot is very

issues. Um but yeah this plot is very useful to showcase the capabilities of these models.

So previously this is 50%. you know if you could if a model can complete the task with 50% of the ch you know of the time to 50% accuracy if you want to actually oneshot the model so you just

ask the model you know implement X or implement Y um and you want the model to do very well then you want to look at the 80% success rate if you look at the

80% success rate it kind of drops quite a lot um so you can see that previously mythos is around 16 17 hours um now it only can do three hours so if you prompt

a model and you want to have like a oneshot example, you know, you just trust the model by just or asking it, you know, implement, I don't know, page rank or something, you know, implement some sort of rag system, you know,

fine-tune a model or something like that. Um, it can only do a task that

that. Um, it can only do a task that will take a human three hours to do. Um,

and so the so that is a problem with AI models. Um, generally speaking, if you

models. Um, generally speaking, if you want to use AI models very well, you need to prompt it at least like, you know, five times or something. Um and

each of those times assuming they're independent um the success rate is much higher if you're prompted many many times right you can't just call the model once and expect it to do work to

do well um you need to call it multiple times um and you can also work out the probability of it like succeeding you know if the model is 50% accurate um then it will be 50% failure then it's 1

minus 0.5 to the power of five or something like that you know if you do five turns and then your success rate jumps to like 97% or something um so you need call the model at least five times

for it to be very effective.

So previously these are linear you know this is a linear trend you know on the y-axis it's just it's not you know it's just linear um if we log it you know if

we log the y-axis you can see that it's more exponential progress um so it's actually a straight line fit to the entire progress of AI models on the meter time horizon um you know benchmark

you can see that you know it's very clear that AI models are getting better and better over time um I als We also added you know GBD 5.6 six with the cheating and no cheating and also claude mythos are you know accentuated that and

you can see I you don't need now you don't need to like you know fake the y-axis you know you don't need to do like a disjoint y-axis um if you do that you can see that you know models are getting better over time um and

supposedly you know if this trend continues these models will get better and better and better better and much better um yeah so so the question is if the trend continues you know that's the

fundamental question Um and it's not just you know one specific task for this benchmark that you can see that models are getting better over time across all benchmarks models are getting better

over time right so like you know GPQA diamond you know it's kind of plateau you know it's kind of already saturated as a benchmark but over time you know it does very well you know every single benchmark you see models are getting

better right live code bench you know maths algorith maths tests um you know even Tesla's you know you know self-driving I guess is also has like a doubling time of 17 months. Um so every

single 17 months the models will get better and better. Um you know double double their capabilities. Um so over time all these models in every single

subject you know every single area it will get better. Um so I guess the main question is you know if we assume every single subject every single

area the models get 100% like you know approaching 100% accuracy is this AGI?

Um so that is one of the fundamental questions that people ask you know if we just get better on benchmarks um is this AGI um what happens if we get better on all benchmarks you know every single

benchmark that human humanity has created it just gets better on all of them. Um yeah but so this is a you know

them. Um yeah but so this is a you know very good plot show well I guess chart showing all of the different types of benchmarks and they all get better over time.

everyone's favorite I guess artificial intell uh you know artificial analysis benchmark showing you know artificial intelligence getting much much better over time as well you know fable I guess

is I guess the best for now um although not everyone can access it currently but anyways it's for now it's the best um and you can see over time that you know these models are getting better over

time as well um and you know like this plot showcases um a very useful indication you know like how do we like you know benchmark you know is this benchmark actually good um in terms of like you know showcasing the

capabilities of models as well. Um and

we'll be also discussing about that as well. Um on the other hand yes models

well. Um on the other hand yes models are getting better over time. Um but

there are some things which models are not very good at still for example long context is not doing very well. Um so

you know most models you might say okay Gemini has 1 million context length. You

know GBD has 1 million context length.

Claude has 1 million context length. But

should you actually use all of the 1 million context length? Um so there are actually benchmarks to showcase that if you use for example GBD 5.5 um you know

if you use 512 context your accuracy reduces to 50%. Um so if you use you know 512 context you will only remember 50% of the facts that you wrote in the

previous context. Um so maybe that's not

previous context. Um so maybe that's not a good idea to use the full context. Um

you can see opus 4.7 um 4.6 4.7 is the very last orange line. Um so at the context length of 256K it goes to 0%. Um

so this might be a benchmark flaw. Um so

maybe don't trust the benchmark too much. Um but it's good to look at the

much. Um but it's good to look at the benchmark overall. You know where is the

benchmark overall. You know where is the model's capabilities for long context.

Um the blue lines I highlighted are open source models. You know deepseek gl 5.1

source models. You know deepseek gl 5.1 other models. Green is Google's models.

other models. Green is Google's models.

Um but you can see in general you know models are models definitely do degrade over long context. Um so if you you know for example if you set like a you know

automatic compaction area I would not suggest you to use all 1 million context maybe maximum 600k or something um and then compact it and then continue your you know coding session um but I would

yeah but in general you know this plot shows that long context still has a very long way to go um and if we want to have long context you know capabilities um

labs I guess will have a lot of time to fix this problem.

Yeah. So another plot is you know just showing open source versus closed source. So open source still has some

source. So open source still has some way to go for this you know long context. Um so open source is blue line

context. Um so open source is blue line and the black lines are like you know closed source models. Um and you can see in general open source does okay but there's definitely much more room for

improvement. Um I guess compared to Opus

improvement. Um I guess compared to Opus 4.7 it's better. Um but you know maybe this benchmark does need maybe there are some flaws in the benchmark as well. Um

yeah, but overall you know this plot shows that long context definitely still has more room for improvement.

And also you know like if you looked at the plot previously you know this meter plot um I'm not sure if you can see that before 01 preview there is actually a

plateau of performance. Um and so if you can see you know GBD4 to GBD40 there's not that much performance improvement.

Um and so this time frame around one year um was when you know the labs were confused on what is next um you know before 01 preview which showed that

reasoning was very important they didn't actually know what to pursue next um and so for one year the models kind of plateaued um and so I call this the intelligence plateau the hypothesis that

you know you know assume that we never have discovered reasoning then maybe air models would have like plateaued um but because we have discovered reasoning you know we have shown that models can do reasoning

capabilities we have continued the trend continuously um and so normally I don't know if this is like luck um or if this is a self fulfilling prophecy um so I don't know if you guys you know the moor

law um you know mos law has continued um not because of the law but because people know that it must continue and so people invest money into the resources to make the law continue um and so this

kind of like shows that you know we might have been in of the world where models have stopped improving. Um but

you know with the launch of 01 preview you know I guess models have went back to trend.

In fact I made a plot showcasing you know assuming we did not discover reasoning or 01 preview. Um then the black line was the supposed you know

capabilities of the models. You can see I made it into a S shape um like a you know a sigmoid type shape. Um and if you know if we didn't discover reasoning then models definitely will taper off in

terms of capabilities right we'll only have a model that's as capable as claw 3.7 sonnet I guess or 01 or something like that um but you know luckily because of reasoning and this new

paradigm of scaling you know the green line is the new scaling law um and you can see previously the black line the doubling time was actually around seven months so every single seven months the

capabilities of the models double um but now it has shrunk to 3.5 months. So

every single 3.5 months you just need to wait 3.5 months and the models will get double better, right? Better by two times. Um and that's quite striking I

times. Um and that's quite striking I guess. Um so the main question though is

guess. Um so the main question though is will the green line continue as a straight line? Um that is a fundamental

straight line? Um that is a fundamental question that labs are still struggling on. you know what happens if the green

on. you know what happens if the green line again you know the green line again goes as a S shape you know that's possible um but you know we don't actually know if this will happen you

know if the green line will continue scaling you know going all the way up to infinity I guess or would it be like an S shape um and this is you know many researchers are you know I guess have

sleepless nights you know what is the next you know what is the next thing afterwards after reasoning after 01 you know what is the next thing afterwards um and you know Many researchers will need to like you know I guess think

about this. Um yeah but you know this

about this. Um yeah but you know this plot is very you know this is one of my favorite plots because it shows that you know AI progress can continue over time with new ideas and innovation.

Oh yes. So does anyone have any questions for the first section? Um yes.

So we came all the way to one trillion right? Do you think the next jump if we

right? Do you think the next jump if we need do we need like 10 trillion parameters when we'll see the jump or hardware will be the limitation that yes that's a great question. So the

question was you know models we're currently at one trillion parameters do we need to go to 10 trillion parameters or more for models to be even more capable? Um so the scaling laws does say

capable? Um so the scaling laws does say that you know if you multiply the parameters and the data size um generally speaking this number if you increase the number you will get the

models become more capable. So yes you can increase the parameters by 10 times and in general your performance will increase. Um however the view is there

increase. Um however the view is there is going to be diminishing returns. Um I

feel like you know it's not just the model size times the data set size. It's

actually a ratio um some sort of like power law when you multiply them. So you

actually get diminishing returns over time. So yes, you're right. If you want

time. So yes, you're right. If you want to have actually I'm not sure the exact law, but if you want to have double capabilities, you do need to 10 times the parameters. Um and then if you want

the parameters. Um and then if you want another double, you have to 10 times it again. So it's 1 to 10 to 100 trillion

again. So it's 1 to 10 to 100 trillion parameters. um if you want maybe that's

parameters. um if you want maybe that's not a good way to scale. Um maybe

instead you know instead of making a 100 trillion parameters some sort of new algorithm or new architecture could solve that problem. Um but you're right

like if you're a lab you want to do something easy and so the easiest path is to just make a 10 trillion parameters. Um but I would say like you

parameters. Um but I would say like you know maybe a new algorithm will be better. Um yeah

better. Um yeah any other questions? Yes.

So you do think that we are approaching the limitation of next token prediction.

That is a good question. I would say that for next token prediction it's very powerful because you can essentially the human language is extremely powerful and it doesn't have to be human

language. It can be you know maths

language. It can be you know maths coding you can just predict the next word and in order to predict the next word or token you need to know everything about that token or that word right so like I think IA was talking

about like you know Ilia Satska he was saying like you know you need to have you need to make a weld model in the model in order to like predict the next word so I still think next word prediction still has a lot of way to go

for example if you see this plot you know if we didn't have reasoning I guess okay maybe it would have plateaued But because we have discovered this new methodology you know reasoning

and trying to like scale even more on next word you know next word prediction we have you know went back to trend um I feel like so the main question is if we don't have next word prediction what is

next um that is the fundamental question most I mean I'm not sure like you know I'm not certain what's what's the next thing I feel like next word prediction is just

extremely powerful because it's very easy to formulate and you can just like you know you can have like you know because attention is very powerful as well. You can have, you know, this

well. You can have, you know, this special cause of attention mechanism and it's very efficient to train. So, I'm

not sure I think the main question is I'm not sure what's next. Um, I guess researchers will like, you know, they're trying to scratch their heads, you know, what is next afterwards? Um,

yeah. I I Yeah. Yes.

Just a follow up on it. Do you feel like we are in the same era like how we attention came out?

Right. So, attention like we don't know what's next.

Yes, that's a fair followup. So, um, you were mentioning how it's kind of like LSTMs or the old AI world. We don't know what's next afterwards. Um, that's a fair point. I feel like

fair point. I feel like so like, you know, previously this example, right? So, after GBD4, it was

example, right? So, after GBD4, it was just pre-training, some, you know, supervised fine tuning, some ROF, you know, some RL um, and they waited one year until 01 preview. So in this one

year of fog you know the fog of war we don't know what what was next and so researchers you know were scrambling you know do we do the reasoning process do we make pre-training better do we make the model bigger and bigger and bigger

you know they tried all these experiments um and reasoning was the one that won I guess um but I think like I think the main question is is the green trend going to

continue at the current time it looks like it's continuing once we see models starting to taper out in intelligence, you know, in capabilities, then we'll go back to the, you know, olden days of

like, you know, this one year waiting period. But I think for now, these

period. But I think for now, these models seem very powerful. Um,

yeah. So, like I'm not sure if this will, I mean, if you look, okay, if you squint at the plot, I guess maybe we're tapering out. Maybe um let's not

tapering out. Maybe um let's not consider the GBD 5.6 cheating example, right? Let's remove that from the plot.

right? Let's remove that from the plot.

Um, but you can see the GBD 5.6 Mythos, you know, 4.6. They're kind of all I guess they're kind of tapering. Um so

maybe as a I mean I don't know if we someone wants to bet on this but you know maybe models have tapered out but we're not sure. So we shall wait a few more months and see. So let's wait 3.5

months. If we wait 3.5 months and see

months. If we wait 3.5 months and see the models do not improve then we have tapered out. Um but remember we only

tapered out. Um but remember we only need to wait 3.5 months. Um so then this law will fail. In fact, if you wait seven months, if you wait seven months, so double the time and models have, you know, just assume you know that dotted

line that if if the models just follow the dotted line, okay, then we have tape it out. And I would agree that, you

it out. And I would agree that, you know, we'll have to design something new in, you know, make some new invention or something like that. Um, but for now, you know, for now looks like it's doing

fine. Um, yeah. Okay, next section. Um,

fine. Um, yeah. Okay, next section. Um,

so every single section we can have questions, so you can ask as many questions as you like. Um the next section we're going to talk about is open versus closed models. Um so

artificial analysis has this very cool plot showcasing the performance of open source. So open source is the blue line.

source. So open source is the blue line.

Um so open source is the blue line and closed source models is the black line.

Um and you can see that open source does lag. You know open source definitely

lag. You know open source definitely lags over time. Um another very good benchmark is called the weird ML benchmark. Um this also shows that open

benchmark. Um this also shows that open source models lag closed source models right the blue line is open source models the green line is closed source models um and you can see over time you

know the x-axis is release date of the model and the y-axis is performance and you can see that open source models kind of lag close source models and why the weird ML benchmark I'm not

sure if you folks actually know about this why the weird ML benchmark um it seems like the weird ML benchmark is a very good indicator better than other benchmarks and the reason the reason why is you know

previously I mentioned you know previously this graph right reasoning the reasoning models are the green line and in the black models are the non-reasoning models and you can see that reasoning models double you know

reduce the time of doubling time to 3.5 months previously it was 7 months um interestingly on the weird ML benchmark these reasoning models didn't actually do better it didn't actually change the

trend um all it did was make slightly better. Um and so this weird ML

better. Um and so this weird ML benchmark seems to be more robust. Um

and that is why you know this benchmark is very useful. Um in fact if you go on the Twitter bus um before GLM 5.2 got released um most you know most of the Twitter people said oh you know deepseek

you know deepse if you see very if you squint okay I think I have a plot. Oh

yes if you squint deepseek and Kimmy are in that little corner over there. um you

know deepseek those three models the three whales are deepseek you know flash deepseek pro I think one of them's max mode or something like that um and also Kim's over there as well so before GLM

5.2 two got released, you know, on the Twitter verse, everyone kept saying that open source models are much worse than closed source models, right? They're not

lagging, you know, they're not just lagging, they're much worse because of this benchmark. Um,

this benchmark. Um, in fact, if you look very closely of the weird ML benchmark, all of the top models are closed source labs, you know, like Fable, you know, GPD 5.5, whatever,

you know, all of these are just very, you know, it shows very clear that open source models are not doing very well in terms of this benchmark. um until GPD 5.2 came along um you know number 15 is

GPD 5.2 and it shows that actually open source has came back um and GPD 5.2 too kind of shocked the world. Um that you know I guess open source has not died.

Um and you know deep yeah so in general this worked very well you know deepse you know GLF2 showed that you know open source does very well still.

You can also filter out by country. So

by country you can see that the black line is United States you know the US models. Um the dark red line is the

models. Um the dark red line is the Chinese labs. Um and you know there's

Chinese labs. Um and you know there's other labs as well. um you know French, South Korean labs and stuff like that.

Um but you know over time it shows that these models um you know the US labs seem to do very well over time. You know

they they're always at the frontier and then the Chinese labs like to catch up over time.

Previously you know I mentioned you know the um you know the plateau before you know before 01 preview got released. If

you actually look at this plot um there is something called the open source draft. Um so after 01 preview got

draft. Um so after 01 preview got released open source labs did not know how to replicate 01 preview. They have

never you know they don't know what is reasoning. So I'm not sure if you okay

reasoning. So I'm not sure if you okay this is a few years back um but on Twitter you know open kept talking about oh you know 01 preview was extremely powerful um you know every single tweet you see every single day you know they

show that 01 preview was very powerful.

Um and so for one I think it was six months to eight months um open source models open source labs they got confused on what to do next. Um but then

as everyone knows deepseek R1 came along um and they showed that even for open source models you can train these models to do reasoning gpo um reinforcement

learning and it does very very well.

In fact, if you take this plot, you know, the the black line minus the blue line, if you just minus it, you get this plot. Um, and you can see this is how

plot. Um, and you can see this is how many months behind open source is. Um,

and you know, over time, um, you can see like, you know, after 01 preview got released, um, you know, it kind of skyrocketed. Um, you know, the open

skyrocketed. Um, you know, the open source models were very, very lagging in terms of, you know, behind closed source models. Um and so like when Deepseek R1

models. Um and so like when Deepseek R1 got released then the open source labs knew okay we can also do uh 01 type reasoning. Um and that is why recently

reasoning. Um and that is why recently you know the the time between closed source labs and open source labs have started decreasing again. Um

yeah so this is slightly outdated. This

is like May. Um so I think now it's actually four months with the release of GLM 5.2. It's around four months now. Um

GLM 5.2. It's around four months now. Um

so open source labs lag behind closed source labs by around four months.

There was actually a very nice plot you know doing some sort of regression. So

some sort of like trend extrapolation.

Um according to this plot um if you extrapolate the trend by December this year open source models will 100% catch up to closed source models by this year

December. Um but you know who knows I

December. Um but you know who knows I guess maybe maybe open source maybe we can have an open source model as powerful as the best closed source model

by December um you know if this trend continues um so I guess the question is will the trend continue um it's always about will the trend continue um

and you know may most of you maybe may know that you know open source some of the open source improvements in technology you know improvements in capabilities are via distillation you know so some of the open source labs

what they like to do is they like to call the models you know core the frontier models like opus or GPD and then use the traces to train your model um so this is a common methodology that

labs like to do um I wouldn't say this is a bad method um but it is a method that you know some closed source labs like to look down upon you know they like to stop you know their view is you know we should not allow these open

source labs to like do this training um and you know get away for free I guess in terms of training cost. Um but you don't actually have to do this approach.

Um so most labs when you do distillation there are two different types of approaches. Um the first approach is you

approaches. Um the first approach is you need to have the logits. You need to actually have access to the full logs.

Um and unfortunately most labs do not actually have that right. So like labs will not give you the full logs. Um

instead you only get the reasoning traces that are summarized um and the final output. Um, and so these, you

final output. Um, and so these, you know, these open source labs, they're not just, you know, they're not just training on the, you know, Opus output, right? That's just, that's silly. What

right? That's just, that's silly. What

they do is they use GRPO or reinforcement learning to recreate the traces. Um, and so because you you have

traces. Um, and so because you you have the final output, which is the answer.

All you need to do is use GPU and RL to create the reasoning trace automatically. Um, and so that's kind of

automatically. Um, and so that's kind of how they train these models. Um, and so you don't actually need to like access the logits or the weights of the model.

um that's not necessary. Um yeah,

and you know, one of the most important factors of you know, these large models is, you know, as models get bigger and bigger and bigger, you can't run them on your local device anymore. Um it's

extremely complicated to run. Um and so we do something called dynamic quantization where essentially you take a model, you quantize them down to one bit. Um but the trick is you don't

bit. Um but the trick is you don't quantize every single layer to one bit.

you quantize some important layers to 16 bit or 8 bit or something like that. Um

and so if you quantize the whole model down to one bit you will get 0% accuracy right 0%. Um but the trick is if you do

right 0%. Um but the trick is if you do dynamic quantization so if you look on the you know this is a three-bit Deepseek model um a three-bit one you get 75.6% 6% accuracy, a three-bit one.

In fact, if you do dynamic one bit, um you get 57% accuracy. Um so we show that you know if you do something called dynamic quantization where you quantize the model down smartly, you can recover

accuracy. Um and this methodology will

accuracy. Um and this methodology will become even more important when models get larger and larger and larger and larger.

if you plot the paro you know efficiency um there if you don't do dynamic if you do you know some other dynamic quantization methods it does okay um but we showed that if you smartly choose the

layers it does even better um I'm not sure if you folks have followed but GLM 5.2 we also released dynamic quantizations for that we showed that GLM 5.2 2 can quantize very well.

So if you look I think this is oh this is an animation. Oh it works. Um but yes you can show the animation you you can see the animation a one bit GLM 5.2

model and this is one bit um and the one bit model is literally 86% smaller. Um

so it's 86% smaller than the full 1.5 terabytes. Um and it still managed to do

terabytes. Um and it still managed to do very well on one of the prompts. Um so

it shows that the models are not dumb.

Right? If you make the model 86% smaller, it does not get 86% dumber. Um,

it only gets 14% less dumb. Um, and so it shows that, you know, if you do special tricks to compress the model, the model still works very well. Um, and

we also compared to Opus, you know, we compared to Opus 4.8, we compared to GBD 5.5. And also, you have to notice that

5.5. And also, you have to notice that for G 5.2, I use high reasoning mode.

You know, for Opus, it's extra high. And

for you know GPD 5.5 is also extra high.

Um and so like you know there are different reasoning modes as well which we can also um see. Um and all of these are oneshot um so we do not like prompt the model like you know 50 times or

something. Um this is just one shot

something. Um this is just one shot directly.

Okay so the next I guess the open source versus close source section is done. I

guess any other questions?

Yes. Um so the question was which parts of the model do we quantize to lower bits versus higher precision. Um so in general um we did actually a lot of research on this. So if you look at the

quen the quen 3.5 architecture there are some layers which is the linear attention layers. Um the linear

attention layers. Um the linear attention layers should never be quantized. If you quantize the linear

quantized. If you quantize the linear attention layers down you will definitely suffer in long context. Um so

in general the linear attention layers need to be left in 8 bit or 16 bit. Um

that's for example um another like if you look at the model layers um some layers can be quantized down heavily to one bit. Um and the reason why is

one bit. Um and the reason why is because these layers are kind of like filler layers. Um and so they don't

filler layers. Um and so they don't actually do anything. Um and in order to check whether a layer does something or not, you do need some sort of collaboration data set. So you need you need to have some sort of like

representative data and pass it into the model um and you can get you can get the um outputs after each layer and then you can see okay does this model at this

specific layer you know does it change that much um and if it doesn't change that much okay maybe just quantize a layer to one bed um but if it does change dramatically then you need to be careful um you you cannot quantize that

down to like one bed or whatever um so there are actually many we actually publish a lot of like blog research on this. Um we show I think there was we also show for example you

cannot quantize the vision layers down.

If you quantize the vision layers down you will make the model really bad. Um

if you give it a you know if you give it a picture of a train it will say it looks like a beach for example. Um and

so it's you should never quantize the vision layers, the audio layers. Um and

only the language the language model layers you can like quantize. Um but

there are many tricks in order to do that. Um yeah

that. Um yeah correct. So the question was if you do

correct. So the question was if you do distillation um you you might have done worse on other topics um but you know only if you for example if you just do coding it will just do good encoding and

then the rest gets very dumb. Um so

that's a fair point. Um so I think that the main trick is you will need to do many many many examples. You will call the model like you know 10 million times. Um and so like the trick is once

times. Um and so like the trick is once you call the middle model 10 million times with high diversity of questions in general um by using the pre-training

argument um the model will do well on other tasks. Um so the reason why

other tasks. Um so the reason why pre-training does very well um is because it has learned so many tasks that it can interpolate the missing holes. Um for example, if you just train

holes. Um for example, if you just train if you just pre-train a model with just maths questions um assume you do only maths. Okay, maybe it's not going to do

maths. Okay, maybe it's not going to do very well, right? And it's not going to do very well on every other task. But

the trick of pre-training is it does maths, coding, law, you know, every single imag, you know, every single topic you can imagine. And the trick is because it has so much knowledge, it

feels the holes of the things that it doesn't know. Um, and so for

doesn't know. Um, and so for distillation, you also need to do the same approach. You need to sample, you

same approach. You need to sample, you need to sample well. Um so for example instead of doing 10 trillion tokens sample you know like 1% um and then call

the model. Um yeah so that's kind of how

the model. Um yeah so that's kind of how the labs are doing that. Um that is a very good question. So instead of doing one big quantization can you instead prune the model like you know delete

some layers entirely. Um so in general from our research pruning does work.

There is a very big problem though. You

need to retrain the model. you need to continuously train a model after pruning because you have deleted an entire layer. Um and so if you delete an entire

layer. Um and so if you delete an entire layer, you will need to do like you know qat or further fine-tuning to push the other to push the other weights to have

more knowledge. So that is the only

more knowledge. So that is the only problem where if you delete layers um if you don't delete layers when you do you know dynamic dynamic quantization it's called post training quantization. So

PTQ you do not need to do any training at all. if you do you know quantization

at all. if you do you know quantization um but if you do prove the layers you do need to train um so that is one of the problems um yeah yes that's a great question so the

question was you know because open source labs you know they use closed source models the gap will never actually go to zero um and so I partially agree and so the main argument

was labs open source labs the easiest way is to do distillation however you know if you for example if you were an open source app you will only use that approach to firstly enter the market but

as longterm you know as long-term safety as a long-term safety net you will not do this approach um instead as a you know instead you will do you know for example generate the answer get the

question for example you know you will get data from a call or scale whatever you know have some sort of like large data labeling army or something I don't know um and so like in general because

currently some of the labs so they don't just do distillation right so they're not just going to call the model 10 trillion times you know and just do distillation. They also augment the

distillation. They also augment the training data with their own approach.

So I will be talking about the GLM approach maybe like later um but they did invent some new approaches to do very good reinforcement learning and GRPO um and because GRPO and

reinforcement learning um you know is open source these labs just use these methodologies to make the models better.

So you don't so distillation is only one part of the training system. Um and it's not I would say that assume distillation disappeared. Okay, maybe open source

disappeared. Okay, maybe open source labs maybe increase you know it's not four four months maybe eight months um but but that's fine because you know we always have some sort of innovative and

new approach you know deepseek might invent something new um and so like you know GLM ki all of them Google you know even the American open source lab they'll have some new innovation um and

so like I think like yes if you stop distillation it will increase you know the you know four months to eight months but I still think that is fine Um it's just a delay you know and then the delay

will go back to like four months. Um

yeah good question. So the question is if

good question. So the question is if dynamic quantization is always better why do people not always do dynamic quantization? Um so

quantization? Um so it depends on the definition of dynamic quantization. So for every single lab

quantization. So for every single lab they will have different approaches to dynamic quantization. In fact, I'm

dynamic quantization. In fact, I'm actually going to talk about that. Um, I

was going to talk about that in the benchmaxing and accuracy minimizing session. So, I'll be talking about that.

session. So, I'll be talking about that.

Um, so I will your question will be answered later. Um, yes. Okay. One more

answered later. Um, yes. Okay. One more

question. Yes. Yes. So, the question was for consumer grade GPUs, you know, what are the open source models in terms of like, you know, the parameter size capabilities and stuff like that. Um, so

for the open source community, you know, the most popular models are probably Quen 3.6 6 35 billion um 27 billion GMA

you know Gemma's 26 billion um GLM 4.7 flash the smallest type models um and I feel like these small models are actually very powerful um so okay I

don't have wait I don't think so I have a plot um but essentially these small models the biggest problem oh actually I'm going to talk about this as well the biggest problem of these small models are they fail very bad at tool calling

because they have tool calling issues um they loop continuously um and the biggest problem is because they're small and that is why they have these problems um but we can counteract this um and so

one of the things I'm going to talk about later is the model becomes not important anymore it's the harness or the tool that is actually the most important thing um how do you actually call the model um that actually affects

the most accuracy of the model um so not actually the model itself um but I'll be talking about that as well um yeah okay I will continue on. Um, there were

always questions after each section. Um,

uh, yes. Oh, yes. The next section, the fun section, throughput maxing. Oh,

actually, I think I did. It's supposed

to be 2x. I don't know. Whatever.

Throughput maxing and and accuracy minimizing. I thought it was like

minimizing. I thought it was like accuracy mining, but there's no such thing. So, it's called accuracy

thing. So, it's called accuracy minimizing for now. Um, yes.

So, this part actually I really like.

Okay. I'm not sure if you guys can see it's a bit oh whatever. Um this shows the parade efficiency of cost of the cost of the model. So cost is um cost is

the x-axis. Um and the y-axis is the

the x-axis. Um and the y-axis is the arena score. So this is like you know

arena score. So this is like you know Ella Marina's arena score. Um and this part I really like. So I don't really you know maybe you see like arena scores you know Ella Marina scores between each

model. I don't really like that. It's

model. I don't really like that. It's

not it's not very easy to see. Instead

the better approach is to plot every single model on two axes cost versus accuracy. Um and you can see Fable does

accuracy. Um and you can see Fable does very well right so Fable does very very well on that plot. Um but you can see there is a paro trend you know like Gemini 3.1 preview is over here you know

Opus 4.6 is over there as well. There

are some other models as well when Fable got released. Okay. Well, now

it's banned, but anyways, when Fable was released, when you know when people tried it, they noticed that it's not that much better in terms of actual

capabilities. Um, you can see, you can

capabilities. Um, you can see, you can see, but however, people really liked the front-end design. You know, they said if you called Fable, it was very,

very good for UI UX front end. Um and in fact if you look at the LM Mariners chart you can see it it was a very big shift in terms of front-end design. Um

GLM 52 is also there if you can see you know it was part of the par paro trend.

Um but in general for these large models they seem to have they're not going to be do they're not going to be doing that much better on general tasks. Um however

for UI and designing Fable seems to have done very very well. Um, and so you should use Fable for your designing. You

you should use Fable for designing, for UI, for UX, whatever, HTML, JavaScript, but you should probably not use Fable for the rest of the tasks because it is

very expensive. Um, so you know, use

very expensive. Um, so you know, use some other models instead.

Um, and you know, however, yes, okay, you know, some other models, you know, like, okay, this, you know, this shows that Fable does very well on UI and UX.

Um but how about over time um you know how what do you know anthropic their view is we need to maximize throughput right maximize throughput but also

maximize accuracy um you know they want to like you know serve more people um but sometimes it doesn't actually work um sometimes they actually reduce accuracy um and so you can see there is

a I don't know if you folks know margin labs um they have this very cool they do they do su bench they benchmark codecs they benchmark codecs and clawed code

with the models. Um, and this is accuracy over time for these models. Um,

and the dotted lines are the release of the new models. Um, so there's actually another um, there was actually a dip in Wait, can you is there Oh, okay. The

mouse is there. Um, I I think it was over here. Um, I think it was over here

over here. Um, I think it was over here that feeble got released. Um, so there was actually another dotted line. Um,

there was actually very interesting trends you can see. The first one is um every single time there is a new model release

this this you know daily tracker seems to decrease in accuracy. Um and so if you want to predict when a model gets released from anthropic you can use this

as an indicator um of when the model gets released. it worked very very well.

gets released. it worked very very well.

Right? So like essentially if you were over here the dipped in accuracy over a very long period of time was because fable got released. Um and over here I think that's opus 4.8 I think. Um I

think yeah I think that's opus 4.8. This

is opus 4. Uh 7 and so on. That's 4.6 I think. I whatever um I don't remember

think. I whatever um I don't remember exactly but um but you can also see that there is ginormous dips of accuracy. Um,

and it's not just like one day or two days, it's for a very long period of time.

This is also Codex. Um, so they also do codeex benchmarks. Um, and you can also

codeex benchmarks. Um, and you can also see that over time. I don't know if you can squint, but you can see that actually Codeex has been getting worse if you plot the trend, right? If you can I don't know if you can squint, but if

you draw a line, it seems to be getting worse. Um, so I'm assuming OpenAI is

worse. Um, so I'm assuming OpenAI is investigating this as well. Um, okay.

So this is different model.

This is codeex.

So this is using 5.5.

This is using model.

Correct. It's the same. So what this benchmark does is you randomly sample 50bench questions. Sweet bench is very

50bench questions. Sweet bench is very large. So you just sample 50 of them and

large. So you just sample 50 of them and then you call the model to answer it. Um

and then you record accuracy. Um and so obviously you know every single day there's like you know daily variations.

Oh, it's not it's not that useful because you're only calling 50 questions. Um, so the trick is to look

questions. Um, so the trick is to look at the trend. Um, and the trend uh h maybe open should investigate this. Um,

and you can see the trend for you know anthropic is also not very good. Um, in

general oh so sorry this is not the same model. Um, these models change my bad.

model. Um, these models change my bad.

Um, so it's the same harness but the model changes. Um, so this dotted line

model changes. Um, so this dotted line is GBD 5.5. Um, so everything over here is GBD 5.5. Everything over here is GBD 5.4. Um I think this is 5.3. Um and so

5.4. Um I think this is 5.3. Um and so on. Um but it seems like the model's

on. Um but it seems like the model's getting worse. So I don't know. This is

getting worse. So I don't know. This is

probably just on this benchmark, right?

On the Sweet Bench Pro benchmark, it's getting worse. Um but you know, I

getting worse. Um but you know, I wouldn't really trust these benchmarks.

The best way is to look at the degradation. You know, the sudden drops.

degradation. You know, the sudden drops.

You know, for example, Codex dramatically dropped over here. I don't

know why. Um and you know clawed you know clawed code was very bad for a few weeks over here or over here right.

Okay. Yes.

Yes there is a confidence interval. I

did not plot it but this is 50 tasks. So

every single day they call a 50 tasks randomly. So they will sample 50 tasks.

randomly. So they will sample 50 tasks.

Um and so you you should not look at this daily. This is daily. So every

this daily. This is daily. So every

single day is 50 questions. Another 50

questions. another 50 questions and so on. Instead, you should do like a

on. Instead, you should do like a rolling average, you know, some sort of rolling, you know, 7-day average. Um,

that's a better number. Yeah,

really. I can see it from here. It's

like decreasing.

It's it's if you look at the if you do the seven moving average, I I'll probably get the pot later. It actually is decreasing.

pot later. It actually is decreasing.

You can see it um if you can see I don't know if you look at the top peaks of the you look at the top peaks and the peaks are decreasing.

Okay, how about the bottom peaks?

Okay, I agree there is random noise. So

the trick is you need to the moving average and if you look at the moving average you can actually see it's decreasing. I I'll probably I'll get the

decreasing. I I'll probably I'll get the plot later. Um you can you can search

plot later. Um you can you can search it. It's so go to Margin Labs, search in

it. It's so go to Margin Labs, search in Margin Labs codeex claw code benchmarks and they do show weekly the weekly trend but I'm just saying this is not this is

not to say that the model is getting worse. This is just to show that

worse. This is just to show that accuracy that you know the sudden dips the accuracy of these models can decrease. Um and the question is why you

decrease. Um and the question is why you know for example why did claude code over a few weeks why did the performance decrease like why that's the fundamental

questions.

So that is one theory. A theory is they might have accident you know that before the model release they are doing testing and so they might have like you know act

you know some of the some of the queries they route to opus 4.8 eight or fable or whatever. And the problem is they did not.

So the main question is if you do route to another model, why did the accuracy decrease? It should actually get better.

decrease? It should actually get better.

And so one of the theories is theory one, they forgot to edit the system prompt. And so the system prompt for

prompt. And so the system prompt for Fable was different, but then they used the wrong system prompt for, you know, for Opus 4.8, and that is why the accuracy decreased. Um and then after

accuracy decreased. Um and then after the model got released the accuracy went back up because they used the correct system prompt. That is one theory. Um

system prompt. That is one theory. Um

the other theory is the other theory is okay we're actually going to talk about this is it's actually they're doing tricks. You know they did quantization

tricks. You know they did quantization but they didn't do dynamic quantization.

They did some dumb quantization. Um you

know they some GPUs are broken for example. You know they use the wrong

example. You know they use the wrong GPUs. Some of them have like you know

GPUs. Some of them have like you know bit flips or something. I don't know. um

they have like a new data center and then that data center just by chance has lower accuracy. Um in fact there is

lower accuracy. Um in fact there is actually okay I'm going to talk about this actually. Um

this actually. Um yeah but there are many many theories like you know possibilities why this could reduce an accuracy. Um actually I I think it's the next plot. Yes the next

plot. Um oh well the next slides. Um so

plot. Um oh well the next slides. Um so

actually when was this? I don't

remember. Um it was a few months ago.

Someone from AMD actually made an issue on chord code you know during this dip.

I think it was during the before um a very large dips in accuracy and they actually asked Claude, you know, they asked the Claude team, why is there a noticeable dip in accuracy? You know,

why why is that?

And Claude actually wrote a in April 23, they actually provided details on why they had reduced in accuracy, right? So

they did a postmortem on what happened with Claude. Um and the reason why is

with Claude. Um and the reason why is because the thinking trace got deleted after the second you know when you when you ask call the second time the thinking trace got deleted. Um and it

had a bad system prompt. Um and they found out that that that was why the accuracy got deleted. Um so somehow in claude code

the second time you ask a question the previous thinking trace got erased. Um

and I don't know I don't even know how they did not find this but oh wow um according to them now is claude now has this internal benchmark so they will use more internal investigations to test

okay next time if there's a new model this won't happen ever again um and you know like these things do happen over time um and so like for this specific example you know cloud code the harness

the harness itself was the problem not the actual model right the harness the thinking trace got deleted and they had a very not a very good system prompt. Um

and that is why the accuracy actually degra um degraded.

So that okay so we found one answer why these models got worse.

They also released in September 2025 right in September 2025 they showed that it was due to okay I didn't okay I didn't put the slide but anyways they showed it was actually due to a hardware

problem. Um so in their compiler um they

problem. Um so in their compiler um they used TPUs. So so Anthropic likes to use

used TPUs. So so Anthropic likes to use TPUs and GPUs. Um they showed that the same software stack for GPUs and TPUs um actually produced different results. Um

and so for the TPUs it actually was different sampling. Um and for the GPUs

different sampling. Um and for the GPUs it was a different sampling mechanism.

Um and so that is actually why they had decrease in accuracy during September sometime. Um because they actually had

sometime. Um because they actually had different hardware. And so you need to

different hardware. And so you need to like Yeah. So like once you have

like Yeah. So like once you have different hardware accuracy also changes.

So I think the main point is the harness the implementation the tool is now the most important. It's not the model right

most important. It's not the model right the model is useless. Most models you know if you look at the model of you know open source versus closed source models are generally the same. The

difference is how clawed code is made you know how codec is made and used. Um

and so that is actually the most important factor. It's not the model

important factor. It's not the model anymore. Um and so like you know as we

anymore. Um and so like you know as we have seen if they have accidentally botched you know if they accidentally botched the harness you will get reduced accuracy. Um and so like you know

accuracy. Um and so like you know definitely you know for large labs as you know I'm sure they are they know these problems and they're working on it. Um but I feel like you know these

it. Um but I feel like you know these are probably you know these are still very hard to fix. Um yeah so hopefully I answered some of people's questions on the harness you know the accuracy um so

there's actually reasons why accuracy got degraded but you know it's not just closource labs during bad across open-source model providers the

accuracy changes so if you look at this plot so this is from open router um this is deepseek v4 pro um so most labs what they want to do most inference providers

what they want to do is they want to serve you the highest throughput, right, with the cheapest price. They want to give you, you know, 60 tokens, 120

tokens, 1,000 tokens per second, right?

They want to give you the fastest. Um,

but did you but did people actually bother to check accuracy? So, that is the fundamental question. You know, you might be getting 10,000 tokens per second and there is no model. Um, so the

main question is you need to be careful of what you use from these inference providers. Um and so for DeepS v4 you

providers. Um and so for DeepS v4 you know there are two benchmarks which open router ran you know yeah it's like sorted it's sorted I think on the gray I think it's sorted on

tower bench um so it's sorted on tower bench um and the green one is GPQA and you can see that in general some of the labs are not you know some of the sorry not labs some of the inference providers

are not doing very well um so you need to like before you before you use a open source model please check the accuracy before you use the open source model. Um

and also one of the biggest problems of this is every single time you know for example a cloud code you know claude code and codeex you can benchmark

accuracy over time. Um and the good thing about closed source labs is they control the supply chain. Um the biggest problem of open source is there are so

many suppliers and providers of these models um that sometimes what happens is people get turned off and they get very annoyed that the open source models do not work very well. Um so everyone you

know in the in the ecosystem people keep saying that closed source labs do much better than open source but it's not because of the model it's because of the inference provider right the inference

provider is to blame that they are causing the downfall of open source because they're giving a bad name for open source um so I would like check you know

whatever favorite inference provider you have um so this this benchmark was run I think yesterday um by open router so this is this is daily data by open

router. Um so whatever favorite

router. Um so whatever favorite inference provider you have please tell them not to you know reduce accuracy that much. Um this is GLM 5.2. Um so you

that much. Um this is GLM 5.2. Um so you know GLM 5.2 as well shows different accuracies. Um you can see so the plot

accuracies. Um you can see so the plot on the right shows most model you know most inference provide okay I keep saying model apps most inference providers are throughput maxing but they

are accuracy minimizing that's where the phrase comes from okay so they do not care about in fact look like you know the highest accuracy is 76.4% and the

lowest is 62.4%. So there is a 10% gap between the back you know between the highest accuracy and the you know lowest accuracy. Um and so like you need to you

accuracy. Um and so like you need to you know as a as a you know as a call out to inference providers you know please increase accuracy you know before trying

to make things faster right you do not want a model to be very dumb um and it's like you know 10,000 tokens per second right we can make it 1 million tokens per second and there is no model um you

know just call a human or something you know make a fake or something so yeah so the main point is we need inference providers to do good in terms of

accuracy otherwise this will make open source have a very bad look um yeah oh okay that's the end of the the second section I guess that was a bit of a rant

um any other questions for this yes for a new organization that's that wants to use like the open source model do you suggest using a you know inference

service provider or do you suggest downloading from hugging face and then using like model or you know some kind server to you know implement yourself like what do you suggest if any new

organization comes and asks you like how do you use open source model that's a great question so when an open source model gets released you know how should you use it in terms of accuracy

throughput or whatever um so in general um in general open source has come a long way so for example we did report bugs in Jamaa 1 ja 2 llama mistro you

know open gdosss every single of those models had bugs Um and so the good thing is you know as we will help the labs before they release a model to fix some

of the issues. So every single model you now have has some of our fixes. So

that's a good thing. Um but in general if you have a open source model I would use Llama CPP for example. I think Llama CPP and Llama server is probably the

most bugfree system. So I would like suggest yes you should download from hugging face. use Llama server, use

hugging face. use Llama server, use Llama, you know, CLI, I don't know, you can use Unsoft Studio, whatever, whatever is your favorite tool. But you

should, yes, you should download from Hugging Base. Um, in terms of like, you

Hugging Base. Um, in terms of like, you know, if you're a large enterprise, generally speaking, what they like to do is they like to wait one week. So most

enterprises, they'll wait one week for all the problems to be fixed. Um, and

then, you know, then they will use the model. But in my view, that is not a

model. But in my view, that is not a good approach. I would say if you okay

good approach. I would say if you okay if everyone waits one week then like how do we fix the bugs? Um because only at scale only at scale then we can see the

bugs. Um and so like in general we need

bugs. Um and so like in general we need everyone to start trying these models earlier. Um and not like you know wait

earlier. Um and not like you know wait one week wait one month you know don't do don't do the waiting approach. Um but

I would say like in general the enterprises what they like to do is just wait one week. Um yeah that's like common practice. Um, yes.

common practice. Um, yes.

So, okay, the question was why would the model performance degrade before a model release? Um,

release? Um, these are just hypothetical question hypothetical theories. So, every single

hypothetical theories. So, every single model has a different system prompt. So,

opus 4.8 8 Opus 4.8 system prompt is very short. Um but Opus 4.7 system

very short. Um but Opus 4.7 system prompter was extremely long. Um so the theory was this is just a theory that anthropic via claude code accidentally

routed some of the models to Opus 4.8 right they use opus 4.8 as testing right they need to test opus 4.8 But they used Opus 4.7 system prompt. So

they used the wrong system prompt and that is why accuracy degraded. That's

one theory. Um, another theory is actually I think that's the actually I thought about it. That's probably the only theory I had. I'm like thinking hm is there another theory? Um,

I guess the harness itself like you know sometimes the harness itself the harness was was designed for Opus 4.7. Um and

during when they were going to release 4.8, they need to collaborate the harness, right? They need to change the harness

right? They need to change the harness um for 4 4.8 to make it work. But the

problem is you're not allowed to publish it, right?

You're not allowed to publish it and give it to people because otherwise people will like, you know, go into Twitter on LinkedIn, you know, everywhere. Oh, I can see 4.8 is going

everywhere. Oh, I can see 4.8 is going to be released. You know, everyone's going to be screaming, you know, 4.8's coming. 4.8's, eights, you know, were

coming. 4.8's, eights, you know, were getting released and so maybe that's why accuracy decreased. It's they update

accuracy decreased. It's they update they did not update the harness. Um or

the other option is they up they already up they silently they silently updated the harness before the new model got released and it regressed you know it reduced accuracy. Um I don't know like

reduced accuracy. Um I don't know like to be honest I you should probably ask anthropic that question. Um or but I think in general in general the dips the dips don't always correspond to like new

model releases. Some of the dips are

model releases. Some of the dips are actual issues like you know the thinking trace got deleted um the system prompt they wrote a wrong I think for the system it's funny I think for the system

prompt they said um they tried to reduce verbosity so they tried to make the model less talkative um and it actually made the model dumber

um and so I think it was just one word they added one word no one sentence I think one sentence in the system prompt that made the model dumber Um, yeah, I don't know if that helps, but I

don't know if anyone else has any like theory. I don't I don't think so anyone

theory. I don't I don't think so anyone even has that many theories on this. Um,

obviously the anthropic engineers will know, but I, you know, they're not going to tell. So, it's just based on

to tell. So, it's just based on hypotheticals. Something to do with the

hypotheticals. Something to do with the system problems, something to do with the harness. Yeah. But I think in

the harness. Yeah. But I think in general, you can also use this plot. You

know, if the performance decreases, most likely a new model is going to be coming. Um, yeah. Any other qu? Yes.

coming. Um, yeah. Any other qu? Yes.

Just to add on that Yes correct.

Correct.

Yes. Exactly.

Exactly. So before a model release, they use a different system prompt for that new model for the old model. And so that is probably why there are some decrease in accuracy. they switch the system

in accuracy. they switch the system prompts around or something like that.

Um and also you know the model itself you know I think 4.8 system prompts is very short. Um it's yeah I think it's

very short. Um it's yeah I think it's like very very short and 4.7 was ginormous. Um and the reason is 4.7 was

ginormous. Um and the reason is 4.7 was like you know I don't know what I don't know what happened but they have this ginormous system prompt and the 4.8 just shrunk it a lot. Um so maybe maybe they

used the 4.7 system prompt I don't know or 4.8 system the short system prompt for 4.8 eight and then they use it for 4.7 and that's why it decreased accuracy. I don't know. Um but yeah,

accuracy. I don't know. Um but yeah, you're correct. Um they do release

you're correct. Um they do release although I think the system prompt they released on the website is for claw.ai.

So the online chat system um the clawed code system prompt is actually different.

Yeah. So I think you need to actually call you need to call claude code you know what is my system prompt and then you print it to like a text file um and then you can like in investigate what

the system prompt is and then you can also override it if you want um yes but it's a different system prompt most likely um yeah

last question if anyone no okay continue on Okay, the next section we're going to be talking about is benchmaxing and

cheating. Um,

cheating. Um, I'm not sure if you folks have seen the deep SWE benchmark. Um, the deep SWE benchmark is a very popular recent

benchmark that shows, you know, the cost is on the X-axis and the Y-axis it is a deep SWE benchmark. It's a new benchmark based on like you know a better

uncontaminated version of Swebench Pro.

Um and in general you can see that you know GBD 5.5 does very well with Fable um you know GLM Opus 4.8 in general right it shows you know this plot shows

that models are getting you know um these the dots are different reasoning modes um I think this is maximum reasoning I think um high extra high you know these are actually different

reasoning um reasoning times as well um but in general you can see that there is a parto efficiency trend right the best model is the one you know to the right

to the top right the better the model to the right to the top is the better the model. Um, so you want the models to do

model. Um, so you want the models to do better and better over time to that to the top right corner.

And you know, I just learned I didn't actually know this. I just learned that Sweetbench Pro when you run this benchmark you use LL you use language

models as a verifier. Um, and I was like confused because like for most benchmarks, for most benchmarks, you should never call another language model to check

whether your answer is right or wrong.

And so for Swedebench Pro, you actually call a language model to verify if your language model was right. Um, and so that is why SweetBench Pro is not a very

good benchmark. Um, one of the problems

good benchmark. Um, one of the problems is is do we need to do sampling? Like

how many verification runs do you need to run to verify if your answer is correct? Do you run it one time? Do you

correct? Do you run it one time? Do you

run it five times? You run it 100 times and take like an average. Um, so I was actually quite shocked that this is actually what happens. I was quite surprised actually. Um, the next

surprised actually. Um, the next question is which model is the verifier?

You know you ask for example you ask opus you know you you benchmark opus 4.8 on swbench pro but which what do you use as a verifier do you use opus 4.8 eight

as the verifier to using the same model itself to verify itself. Um and so like this I was like quite surprised actually that this is how benchmarks work. Um and

actually quite disappointed. Um but

anyways obviously you can go the other approach. You can do human verification.

approach. You can do human verification.

Um you know everyone in the room I'll give you the bench you know and just tell you guys to verify it. Um you could do that I guess. Um and also what happens if the verification changes

every day? Um you know remember

every day? Um you know remember previously models you know every single day models get better or worse. um what

happens what happens if you run what happens if you run the verification when the model was doing very bad right you will actually have different SWE numbers um and so like I'm actually quite

surprised this is what the industry does um you know run bench pro but using anonymous is verifies that is definitely not a good idea um but anyways people do

it whatever um in fact according to deepu um if you do if you do verification using language models

Sweet Bench Pro has a 8.5% false positive rate. Um, and a false positive rate means that the LLM verifier said that the model was

correct, but it was actually wrong. Um,

and so 8.5% of the time it would do this. Um, the false negative rate is

this. Um, the false negative rate is even worse at 24%. Um, this means that the verifier said that the model was wrong, but it was actually right. Um and

so you can see that SweetBench Pro is a very bad benchmark. Um and so Deep Sweet showed that they have in you know they fixed the problem you know um by

reducing the false positive rate and the false negative rate to you know 1%.

Um in fact some examples of cheating um I you know this is actually quite surprising um but in the bench pro benchmark you get you get like a GitHub

question you know a GitHub issue you call the model to solve that GitHub issue but did you know that in Swebench Pro you get the full Git history so you get

the you get the actual answer as well um so I'm like I'm actually quite I was actually quite shocked to learn this um that during these models you give the answer and the question like obviously

the model will cheat. Um and so like this is definitely a very bad benchmark.

Um you know you should never ever ever ever give the model the answer. Um and

so very silly. Um but yes this happens a lot. Um and you do not want the model to

lot. Um and you do not want the model to literally see the solution, right? That

is a terrible approach. Um the other problems that you get get like false positives is you know the PR tests you know the the GitHub the GitHub issue

tests are very weak. Um so you know at the final conclusion you know when the GitHub when the GitHub issue is closed with a pull request the tests that the maintainer wrote are not very good. Um

and so the problem of that is you know if you have tests which are very weak then you know the model does very well not very good. Um and obviously the worst part is the model will like bypass

some tests. It will skip some um and

some tests. It will skip some um and that is not a very good approach.

In fact um deep suite actually showed how many times a model cheats by looking at the full git history you know directly going to the answer. Um you can

see opus 4.7.

So the purple bars show cheating by models. Um ah it looks like Jubilee 5.5

models. Um ah it looks like Jubilee 5.5 never cheats. It looks like it um h okay

never cheats. It looks like it um h okay maybe we should use GP 5.5. Um you know actually this is actually very interesting. There are some people which

interesting. There are some people which think that if you cheat that's actually good. Um and the reason why it's good is

good. Um and the reason why it's good is it means that Opus 4.7 already know like if you give it the full Git history you should be able to like you gave it to them right you gave Opus the full Git

history it should find the solution there right it should just directly skip over to the solution. So it's that's what people think you know people have a view that

the humans gave Opus 4.7 the full gate history so it should cheat right you you you designed it to cheat um so in

general cord models seem to cheat more um and open AI models seem to cheat less in general um so it depends on you you know if you want a model to cheat or not

um and the definition of the word cheat is also very you know charged so I guess it depends on what the word cheating means um you know for false negatives remember

Swebench Pro calls a language model to verify if your answer is correct um and so sometimes it's not very good you know sometimes you have unrelated tests that

fail um you forgot you know sometimes when you write tests you forgot about the tests which have helpers you know helper functions and you just skip that um so there are many issues and this I

think this was 20 yeah so 24% % of the time, 24% of the time, the model says, the verifier says your model was wrong, but it was actually correct. So, this is

another problem.

And even worse, the harness itself can change accuracy. So, when you benchmark

change accuracy. So, when you benchmark using Swebench Pro, like you need to have one agent or one harness for all models, right? How do you create a

models, right? How do you create a generalized control environment for these models? Um and so you can see like

these models? Um and so you can see like you know for example DeepSu showed if you use clawed code you get 40% accuracy but then if you use their own so it's a

special harness you can get 50% accuracy um Gemini for example right if you use Gemini CLI you get 20% accuracy but if you use their one you know the the

control environment you can get 40% accuracy um and so in general for these benchmarks you also need to have a controlled environment. Um, and

that is also another problem.

And with Deep Suite, they showed by using this benchmark, by solving, you know, by stopping cheating, you know, by, you know, if we remove cheating, if

we remove, you know, these other issues, you can see the models, you know, the models are not saturated anymore, right?

You can see the models are very different in terms of the capabilities.

According to this benchmark, GBD 5.5 is the best according to this one. Um I

don't Oh, this is not updated. Um for

4.8 I think is over here or something.

Um but yes, this benchmark shows core taiku is 0%.

Um accuracy, right? It's terrible, I guess. Um but yeah, this benchmark just

guess. Um but yeah, this benchmark just show okay the main question is do you trust this benchmark? That is another question. Um

question. Um there is other benchmarks, right? So

cognition released a frontier code benchmark which also tries to solve the same questions for benchm you know for cheating and benchmarks. Um and what they showed is you can fix contamination. And how do you fix

contamination. And how do you fix contamination? You ask, you know, you

contamination? You ask, you know, you ask Cognition's team, which is full of like, you know, national Olympiads and, you know, international Olympiads. They

manually checked every single question um themselves, you know, and removed bad questions, you know, bad examples. Um

and they also showed that their questions are much more diverse, right?

So, Frontier Code has many different other languages. Um and they showed with

other languages. Um and they showed with diversity you know with more diverse programming languages um and by reducing contamination they also have a benchmark um and

according to their benchmark opus 4.8 is the best right for 14.5% accuracy juby 5.5 is 7.2 to accuracy.

Um, and this is the diamond one, right?

So, this is the 50 the 50 hardest questions. Um, the main benchmark is 100

questions. Um, the main benchmark is 100 questions and the extended is 150. Um,

and so according to them, you know, Claude does the best according to them.

But also according to them, Frontier code seems to be better than Deep Suite.

Right? The benchmark that I showed previously, Deepswuite, this one um you know according to Frontier Code, so the cognition team, their benchmark is better than Deepswuite, right? According

to them, according to them, Deep SW's false positive rate is 44.9%.

But remember what did Deepswu say? They

said the false positive rate was I don't remember what what did they say? Um they

said that it was 0.3%.

Right? So deep said deep said their false positive rate is 0.3%. But

Frontier code said that Deep SWE's false positive rate was 44.9%.

Um so you know there is some competition I guess between benchmarking labs um well cognition is not a benchmarking lab but like you know between companies um so the main

question is who do we trust you know do we trust Frontier codes benchmarks? Do

we trust Deep Swiss benchmarks? Do we

trust Bench? You know, who do we trust?

And that is a very important question.

Um, you know, my take is like, you know, like let's just take an average of everyone. Take an average of everyone

everyone. Take an average of everyone and you'll probably get the best answer.

You know, who is actually doing the best. Um, yeah, but this is actually

best. Um, yeah, but this is actually very interesting. Um, you know, it show

very interesting. Um, you know, it show Okay, so according to them, the false negative rate for Deep Suite is correct.

You know, 1.2%. But my interest, you know, I probably, you know, my main question is why is the false positive rate so high for deep according to according to Frontier Bench, Deep Sweet

is even worse than Sweet Bench Pro.

That's what they're trying to say, I guess, for for the false positive rate.

Um yeah.

And even worse, there is another benchmark called Frontier Math. Um, so

Frontier Math is by Epoch AI. Um so they they have this math benchmark with different tiers you know tier one, tier two, tier three, tier four. So tier four

is the hardest. Um but the benchmark itself was botched. Um and so they actually had to release a corrected version of their benchmark. Um I think

this was one month ago um or something.

Um so they showed that their benchmark questions were fully wrong. Um, and you can see that if you correct the benchmark, if you correct the benchmark,

the accuracy for GBD 5.5 jumps from 50% to 80% or something. Um, and so now you kind of trust the benchmark.

And they showed in a tweet, oh, it's June 12. Oh, it's only two weeks ago.

June 12. Oh, it's only two weeks ago.

Um, so in June 12, they showed that the reason why they did bad on the benchmarks is they they did the answer extraction incorrectly. For example,

extraction incorrectly. For example, they did, you know, they had unclear questions. They had the incorrect sign.

questions. They had the incorrect sign.

So, for example, they said the model said 12, but it should be actually minus 12 and they forgot to cut the minus sign. Um, they have one-off errors. Um,

sign. Um, they have one-off errors. Um,

yeah, there's many problems with the benchmark. Um, and so they fixed their

benchmark. Um, and so they fixed their benchmark um, just recently.

In fact, you know, it's actually quite funny. This was just two weeks ago.

funny. This was just two weeks ago.

Have you guys heard of hugging faces math verify which was one year ago? Um

and hugging base showed that in fact these benchmarks when you do math questions they always do bad and the reason why is because there's many problems right the formatting is

incorrect um you know the extraction of the fraction is wrong um you know the sign is failed extraction there's many many many problems of mathematical extraction and to be honest I feel like

it's like kind of a reinventing the wheel or you know rediscovery um but hugging base actually published this one year ago and epoch just fixed it 2 weeks

ago. Um so you know benchmarking labs

ago. Um so you know benchmarking labs definitely need more you know they need to investigate literature more I think.

Um in fact according to hugging face math verify you know if you use if you the green bar the green bar is if you do not use hugging faces's verification

system you know to fix the benchmark. If

you do fix the benchmark, you can see accuracy dramatically increases, right?

For example, for Quen, for Quen, the accuracy was 10%, now it's 25%. Um, and

so you need to, so that means the open source models are not dumb. They just

have different they output a different format. Um, and so one of the problems

format. Um, and so one of the problems is how do we actually actually like, you know, pass these different formats?

In fact, it's even worse. Um, no, I think I tweeted, oh, I tweeted this in August 2024. Um, that if you if you use

August 2024. Um, that if you if you use different tokenization, you can also have different accuracy. Um, in fact, for MLOU, if you use spaces, you

increase accuracy by 0.4%. Um, it might not sound like a lot, but the point is by these very dumb things like, you know, using spaces or, you know, minus

12 becomes 12. Um and all of these like dumb little small things, the accuracy of these benchmarks can change over time. Um and so like the main question

time. Um and so like the main question is you know how do we make benchmarking labs and benchmarking companies you know how do we make them more reliable um and

you know more trustworthy.

Oh okay that's I guess the section for the benchmarking part. Any other

questions for that section? Um

questions. Yes.

That's a great question. So the question is how do we how can we trust these benchmarking companies or like what other types of benchmarks can we do to make it trustworthy? Um so that is

actually a very good question. The main

question for benchmarks is you need to satisfy two conditions. The first

condition is the benchmark must not must not be benchmaxable. Right? How do you make a benchmark that is extremely hard to benchmark, right? How do we like not

get 100% accuracy? And the second question is how do we make the benchmark um verifiable, right? So how do we make the benchmark you can you can also verify that the answer is in fact

correct, right? You remember Swebench

correct, right? You remember Swebench Pro is dumb because you call the language model itself to verify itself.

Um so that is not good. Um so the main question is those two questions. Um, and

so one good example, this is just a dumb example.

Randomly create maths questions.

Sample for example. Okay, this is okay, this is probably not a good benchmark.

You automatically create maths questions. Um, we can sample infinity,

questions. Um, we can sample infinity, right? We can sample infinite maths

right? We can sample infinite maths questions, right? 2+ 2, 4 plus 4, you

questions, right? 2+ 2, 4 plus 4, you know, any single number added together.

That's one question. Can you verify this? Yes, you can. Right? You can call

this? Yes, you can. Right? You can call a calculator to verify what is 2 plus two. Can this be benchmaxible?

two. Can this be benchmaxible?

Hard. And the reason why hard is because the sampling space is infinity, right?

It can be 2 plus 2, 1,00 plus 101, right? It can you you don't have to do

right? It can you you don't have to do plus, right? You can do 1,00 times 1,00.

plus, right? You can do 1,00 times 1,00.

And so that's one way make a benchmark which is very hard to cheat but also easy to verify. So some sort of math question. Um, the other one, for

question. Um, the other one, for example, is um, okay, maybe this is not a good example.

I'm just making this one up on the spot.

Tell the model to create a poem in 70 words and you must use the word happy.

Can you verify this? Yes, you can. Is

happy in the, you know, generation? If

yes, plus one. Also, you can count how many words, right? You can count, okay, is there 70 words? Um, so you can do these type of approaches. And is this benchmaxable? No. It's it's very hard to

benchmaxable? No. It's it's very hard to benchmark because you can say 70 words, 69 words, 68 words, 102 words, 1,000 words, right? It doesn't have to be

words, right? It doesn't have to be happy. It can be you must have two

happy. It can be you must have two words, you must have three words. Um, so

some some sort of benchmark where it's very hard to benchmark. Um

yeah, in my view I think that's that's probably going to be the most important benchmark and I don't I don't think so anyone has actually made this yet. Um I

don't know maybe someone in the audience or you know you guys can go as teams I don't know make a startup or something you know do that. Um and I feel like that benchmark will be very very important. Um yeah

important. Um yeah benchmarks we can trust today none of them. take an average of all of them. To

them. take an average of all of them. To

be honest, probably the best approach is just vibe uh vibe checking. Try all of them and see which one you like the best. Um to be completely honest, I just

best. Um to be completely honest, I just you know like these benchmarks h like the main the main issue I have with

benchmarks is for example um you know I mean like this one right this one I mean even every single day the benchmark can change. So we can't

trust the benchmarks anymore. So my

fundamental view is do not trust any benchmarks.

Take an average and then okay then main question is who's taking the average? I

guess artificial artificial analysis has some average. The only problem is they

some average. The only problem is they have some weightings for the weight. Um

you know each benchmark has a weight. So

now the question is you know what is the waiting of each benchmark. You know you can't just take like a dumb average. Um

you know you can't just say you know 10 benchmarks divided by 10. Um that's

probably not going to work. So the main question is how do you even do the waiting? That's another problem. Um, so

waiting? That's another problem. Um, so

I think in general it's based on vibe checking, I guess. Yeah, I guess I don't have an answer for that. Um,

any other questions? Yes.

question.

Yes.

So that way Good matter.

You're correct. So the question was in terms of because we bench pro for example you call a model. The question

is what model? Could it be 4.8? Could it

be GB 5.5 and you call this model to verify the benchmark? Um you and so the question was can you use an open source model instead? So then now you you have

model instead? So then now you you have a controlled environment. So yes you can. But remember there is a problem

can. But remember there is a problem because even open source models itself have bugs times you know the inference engines have bugs times the inference

providers have bugs and accuracy degradation. So it's you're correct. Um

degradation. So it's you're correct. Um

so the main question is we need to have some one or some organization you know some person or some whatever committee that we can investigate you know which

engine did you use do not update the engine you know the engine must be the same you know the weights must have not changed so there's many many many problems with this approach um but I do agree as open you can use an open source

model but it's not it doesn't solve the other problems um yeah does that Okay.

Um, so the next section I'm going to be talking about is cyber security and regulation. Um, this is a interesting

regulation. Um, this is a interesting topic. Um, so I'm not sure if you have

topic. Um, so I'm not sure if you have all folks have seen this plot. It shows

the AI security institutes. Um, I think this is from the UK. Um, they show the performance of models based on some cyber security task. Um, and they show

that mythos preview seems to be the best. Um, you know, with GBD 5.5 cybar,

best. Um, you know, with GBD 5.5 cybar, you know, preview and so on. Um, they

show this benchmark. Uh

and again previously as I mentioned weird ML is a better ben in my view okay this is just my take weird ML is a better benchmark in general for benchmarking intelligence on models and

the reason why is because it doesn't actually it doesn't actually follow the trend of reasoning versus non-reasoning remembering reasoning previously I think I okay I don't have it um reasoning um

the reasoning models doubling time reduced by half to 3.5 months So remember, you just need to wait 3.5 months and the models capabilities will double. Um and the non-reasoning was 7

double. Um and the non-reasoning was 7 months. Um so you need to wait seven

months. Um so you need to wait seven months for the models to double in capability. Um but weird ML did not

capability. Um but weird ML did not actually have this trend. Um the weird ML benchmark showed that actually the trend was like there is no trend. Um,

and I think I'll just talk about this, you know, like one of the biggest problems of benchmarks is you need to constantly reinvent yourself and do reweings of combinations of benchmarks.

For example, artificial analysis just recently released, you know, their new v4.1 benchmark and they showed the waiting of the benchmarks. Um, you know,

GDP vow is 20%, terminal bench is 16% and so on. Um and so they they designed these numbers as waitings for each of those benchmarks and then they've averaged it up together. Um so the main question is how do you actually

determine these numbers? Um and so this is more like a human approach. You know

you have to determine these numbers. um

you know arc AGI kind of saturated on ARC AGI 1 and so that's why we have ARC AGI 2 and that is also why we have ARC AGI 3 and my you

know I guess once ARC AGI 3 is saturated then we have ARC AGI 4 5 6 7 whatever um and the main point is once you have benchmarks is it called good art I don't remember um the good the benchmark

itself becomes useless because you know models will start benchmarking on this so one of the biggest problems of these larger models for cyber security for

example um is mythos actually dramatically went out of the trend um and that is why you know many people are afraid of these you know mythos you know

GPD 5 point 5.6 you they're afraid of these models because it went out of trend um you can see that mythos dramatically went out of trend um and you know even you know you know GP 5.6

didn't really release that many benchmarks because it was in preview mode. Um, so this is from their system

mode. Um, so this is from their system card. They showed for cyber security

card. They showed for cyber security that Guby 5.6 does very very well.

Um, in fact because Guby because Guby 5.6 they I think they only did terminal bench as their benchmark. They did not benchmark on anything else. Um, they did have in their system card they did have

one benchmark which is very important.

Um, and this is called the internal research debugging evaluation. Um, and

this is OpenAI's own set of set of questions. So, you know, the custom open

questions. So, you know, the custom open source, you know, if you want to, it's their own set of 10 questions or whatever that they benchmarked GBD 5.6 on. Um, and according to them, it does

on. Um, and according to them, it does very very it does better. Okay, I was going to say very, very well, but it's not. Um, it does better. Um, and you can

not. Um, it does better. Um, and you can see that GBD, it's actually kind of interesting. GBD 5.5 did worse than GBD

interesting. GBD 5.5 did worse than GBD 5.5 a four um for OpenAI's own internal um research evaluation um and you know GBD 5.6 definitely does much better

right you can see that the G GBD 5.6 soul, you know, if you extend it, it does much better. Um, but interestingly, Terara does better um somewhat

sometimes. Um, yeah.

sometimes. Um, yeah.

And, you know, one of the biggest problems of these models that are getting getting better and better and better is I don't know if you guys know that, you know, open-source exploits are getting worse and worse and worse. Um

and so the high exploit ratio you know number of critical vulnerabilities that were discovered has skyrocketed you know recently you know every single week or

day some sort of open source package gets compromised um and they actually you know this plot shows that it's getting very problematic um and so you

know claude mythos was released at this dotted line where you know most people they're not sure if it's because of claude mythos that these vulnerabilities are increasing most likely it's because open source you know we use lots of

models call them many many many many times and we can you know automatically find exploits in these models but you know there is actually another

point so in hacken news someone posted about this um is it just mythos and juby 5.6 six that do good on finding cyber

security issues. It's not actually open

security issues. It's not actually open source models also do very well. Um open

source models do extremely well in finding cyber security threats and issues. Um you know there is some

issues. Um you know there is some discussion on hacker news you know is this actually true or false? Um but you know according to some you know some researchers and cyber security people

the main reason why you know mythos looked like it was very good on cyber security is because they bothered to actually check the open source code. Um

and so if you actually give the open source models the full code base of these open source libraries they will find the bugs you know they will find cyber security issues. Um and all you

need to do is core the model. Um and so I feel like you know that's the fundamental problem is mythos seems very powerful not because the model is powerful but because they actually

bothered to test on all open source repos. Um and so if you do you know if

repos. Um and so if you do you know if you call all these open source models to detect for bugs for cyber security issues you will find bugs

and you know as as you know recently you know as everyone knows fable is still banned for the majority of everyone. Um,

and GBD 5.6, you know, is delayed a staggered release, right? So like Guby 5.6 preview was on Friday, right? So

like a few days ago, and they said they're not going to be releasing to everyone. Um, and the main questions

everyone. Um, and the main questions are, you know, in the open source world, in the clos world, people are asking, do we need a license to use these AI models

for everyone? You know, like everyone in

for everyone? You know, like everyone in this room now, we have to have a license to use the models, like a driver's license. Um, do we need to get that? um

license. Um, do we need to get that? um

is there going to be a delay in all of these releases? So every single time

these releases? So every single time when a new model gets released only the trusted providers get these models. Um

the next most important question how about open-source models you know okay the government the US government currently is like you know trying to like control Fable GPD 5.6

The main question now is what do we do about open source models? You know, open models, open weight models. What will

the government do to control the open source space? To be completely honest, I

source space? To be completely honest, I was quite surprised the government acted this early um in doing GBD 5.6 and fable control, right? I thought it was like

control, right? I thought it was like maybe the end of the year or next year, but it seems like it's now. Um so the next question is what will happen to open source models? Will the government

start controlling open source models? Um

and the fundamental question is what defines frontier intelligence like the reason why the government is you know they're controlling these models is because they're very very powerful. Um

so the main question is what actually defines intelligence? You know which

defines intelligence? You know which benchmark do we use? Is it just based on one trillion parameters like you know how do we define whether a model can be banned or unbanned? Um and that is a

very very important question. Um and we will we have a dark web of open models now you know do we need to torrent open models? Um and the most important

models? Um and the most important question what is inference what are inference providers going to do now you know assuming assuming that the government has some sort of regulation

on even open models. Um what is the inference prov what are they going to do? You know what are the inference

do? You know what are the inference providers going to do? Do they need to have license? Do they need to check that

have license? Do they need to check that everyone has a license before you can use the model? Um or something like that. Um and so like you know these are

that. Um and so like you know these are very important questions that you know the government is currently like you know and the industry you know the entire AI ecosystem and industry we are trying to like you know what are the

answers to these questions. Um and

obviously you know if you were the government if I was the government it makes sense you know they do not want their critical infrastructure to be hacked. You know, remember open- source

hacked. You know, remember open- source exploits are skyrocketing. If you change that y-axis, you know, not open source exploits, but like critical infrastructure exploits, you know, obviously the government's scared. Um,

so it makes sense for them to like stagger the release. Um, but the main question is, you know, we're still in this we're still in this fog of war type approach, you know. Okay, not fog of war, just fog, a foggy, you know, we

don't know what will happen for regulation. Um, yeah, that's very

regulation. Um, yeah, that's very problematic. Um yeah. Oh okay. Anyone

problematic. Um yeah. Oh okay. Anyone

have any questions for cyber security regulation policy or whatever? Um or any takes as well questions?

Yes.

That is a good question. So is it is open source so the scare of open source models is it because you know anthropic keeps screaming about open source is bad open source is bad you know every single

day open source is bad um yes and no I feel like it's true that you know there are some players in the closed source industry they want to shut

down the open source ecosystem their view is if you give open source to anyone they will start hacking you know critical infrastructure they will start doing bad behavior. Um, and so that's

kind of their view. Um, so yes, I agree that some of the closed source labs have caused this problem. Um, but it's actually kind of funny because currently

the government is regulating them first and open source is still a question mark. Um, and so like it's kind of like

mark. Um, and so like it's kind of like I don't know, they probably stabbed themselves in the foot or something. I

don't know whatever whatever the phrase is. Um but I feel like it's they did

is. Um but I feel like it's they did cause some controversy in terms of like saying open source is bad but in general open source models are actually good. Um

so you could I mean theoretically you can use an open source model and you know run this on all repos and you will

be able to find exploits and you can exploit. So they're not wrong. Um but I

exploit. So they're not wrong. Um but I feel like you know who has the infrastructure to do this? um you know, GitHub might automatically detect you and ban you or something. I don't know.

There's many there's many um layers of security for each section. Um and so like I I don't know. I I feel like it's somewhat overblown, but it is it is it's

not 0% probability. So it is a problem.

Um yeah, if that answers your question, but okay. Yes. So now we're going to be

but okay. Yes. So now we're going to be talking about kernels. Um

so previously you know this is my favorite plot as usual. Um you know if we were in a different future you know if we were in a different timeline that

we did not discover 01 preview models would have plateaued. I think that's the fundamental point of this plot. It shows

that if we have never discovered reasoning we have never discovered 01 whatever we will have plateaued. We will have plateaued in terms of accuracy. Um and

that is not good. Um and because we have discovered this new paradigm of scaling, you know, models have continuously scaled even further. Um but my take is

the reason why we have stopped scaling um based on you know the old approach is because the old approach only focused on hardware optimizations.

We now have to move over to software optimizations and algorithmic optimizations. Um we you know we need to

optimizations. Um we you know we need to have new inventions of how do we scale AI even further. Um and we can't just rely on doing 10 trillion parameters or you know making the model bigger and

bigger and bigger bigger. Um for example you know we have to do float a reinforcement learning. Um so if pytorch

reinforcement learning. Um so if pytorch has this methodology where you can do floatate float for different precisions to make training faster. Um and that is one way. Um another way for example as a

one way. Um another way for example as a software approach for example as I previously said we found some bit you know issues in gradient accumulation. Um

so when you do gradient accumulation um it was actually it was not calculated correctly during the loss calculation.

Um and you can actually increase accuracy by 1 to 3% if you fix this small little issue.

Yeah. So like you know the universal gradient accumulation bug fix was a software fix. It is not a hardware fix.

software fix. It is not a hardware fix.

Um and so the fundamental view is you need to do more and more software changes. Right? Another one for example

changes. Right? Another one for example Snowflake we collaborated them to make context long context fine-tuning 500k contact length this was all software improvements um another one is you know

12 times faster MLB training this is another software improvement um deepseeek you know they released something called deep spark which was just a few days um and they showed that

they can make inference you know 50 50 to 600% faster so six times faster than just normal MTP um and so this is a software ware methodology, right? Not a

hardware methodology.

And you know, diffusion Gemma, right?

Gemma released a new diffusion model showcasing that you can get 2,000 tokens per second by using a new architecture, right? So using diffusion LLMs to do

right? So using diffusion LLMs to do faster inference and again this is a software change. And my main point is is

software change. And my main point is is that in general, hardware innovations are getting less and less important. Um

and hardware innovations are actually slowing down. Um so it's actually kind

slowing down. Um so it's actually kind of interesting intelligence you know the scaling of you know intelligence in general it's kind of like Mo's law um

it's kind of like a there is a relentless progress relentless approach to increase intelligence and the same with Mo's law um and so like in general you can see that you this is Mo's law

over here the number of transistors has continuously increased um but you know single performance is not increasing it has staggered Um and so this is kind of

like you know this kind of reminds me of you know this plot right scaling intelligence in terms of parameters probably has plateaued most likely you know hardware performance pre-training

whatever we now need to go into this new reasoning paradigm to scale even further um so it kind of is like similar to the moors law type graph um kind of um and

you can see if you see on this side the number representation of GP so my GPU is getting faster and faster and faster, right? It's not actually the GPU itself

right? It's not actually the GPU itself that's getting faster and faster and faster. Um, it's the represent number

faster. Um, it's the represent number representation, right? So like they

representation, right? So like they changed from float 32 all the way to float 4. Um, and this made GPUs 32 times

float 4. Um, and this made GPUs 32 times faster. Um, so it's not eight times

faster. Um, so it's not eight times faster, right? It's not 32 divided by 4

faster, right? It's not 32 divided by 4 is eight times faster. It's 32 times faster. And the reason why is because of

faster. And the reason why is because of tensores, um, you know, the smaller mantesses, um, and so on. Um, and so like you can actually see, you know, even tensors with the introduction of

tensores, it made the GPUs 12 times faster and so on. Actually, if you made the GPU smaller and smaller and smaller, it only made it three times faster. It's not

even that important anymore. Um, and if you look at this plot, we are now at float 4. So most of the GPUs that we

float 4. So most of the GPUs that we have now are at float four. What is

next? Are we going to be having float three, float two, float one? Are we

going to have float zero? Okay, no such thing. But anyways, the point is

thing. But anyways, the point is hardware is kind of at its limits, right? We're already at float 4. What is

right? We're already at float 4. What is

next? There is nothing next. Um, and so the so the answer to this question is there is nothing next. Um, and so now we need to move over to software, right?

How do we make new algorithms? How do we make new methodologies to continue scaling? Um, I also made this table,

scaling? Um, I also made this table, right? I previously said why is you know

right? I previously said why is you know you use float 32 um we change it to float 4 why is it why is it not eight times faster um and instead it's 32

times faster right why is it 32 times faster and the reason is because when you use when you do floatingoint precision you have an exponent and a

menta um and the transistor space the transistor space is the exponent plus the menta squared um and so the trick is if you make them in Tesla smaller and

smaller and smaller, you square their number of improvements, right? So, float 32, float 32, you

right? So, float 32, float 32, you needed 537 transistors around, right?

537 transistors. Um, to go from float 32 to float 16, you only need 105 transistors. So, actually you made you

transistors. So, actually you made you made the number of transistors five times more, right? So, not two times, it's five times. Um, and so on so on so

on. Um, so you know, I guess you can go

on. Um, so you know, I guess you can go to 1.58 bit. I guess you can do that.

Um, but it's actually kind of interesting because 1.58 bit um is actually not that much faster. Um, so

1.58 bit is actually not that much faster um than float 8. Um, if you use um, you know, seven seven exponent and Messa 2. Um, there is another 1.58 bit

Messa 2. Um, there is another 1.58 bit which you use float 4. Um, so float 4 is 179 times faster than float 32. Um and

the main question is we are already at three transistors right we are already around three transistors what are we going to do next two transistors or like one transistor so don't like you know

most likely GPUs are not going to be getting faster um that's the fundamental question of this plot so GPUs are not going to be getting faster instead we need to focus on kernels

right how do we make better kernels better algorithms how do we scale this instead right don't do don't do hardware optimizations anymore. Instead, how do

optimizations anymore. Instead, how do we do, you know, these optimizations?

Um, and so one of my favorite tools to use, you know, everyone should use this is just use torch compile. Um, so in my, you know, it's the modern, you know, the

modern time, do not, as advice, do not learn how to write custom kernels. That

is advice. Do not do kernel writing. Um

and the reason why is because torch compile will take over all of kernel writing. Um so you can see for example

writing. Um so you can see for example this plot um torch compile was a red line right performance it doesn't look like it's doing very well right it does not look like it's doing very well

versus handwritten kernels right handwritten kernels are the other ones right so torch compile doesn't look like it's doing very well but that's because that's an old PyTorch version if you

have a newer PyTorch version torch compile wins dramatically right that's the orange line um and all of these are handwritten kernels. Oh, the okay the

handwritten kernels. Oh, the okay the black line is torch compile plus no fusion. Um so that's another torch

fusion. Um so that's another torch compile method. Um but the red line, the

compile method. Um but the red line, the green line and the blue line okay the the blue line is just no torch compile just normal PyTorch. Um but the green

line and the black the green line and the red line are handwritten kernels and you can see it does even worse than torch compile. So like my viewers like

torch compile. So like my viewers like what's the point of writing kernels?

Torch compile does even better than you.

Um so the main point is you should always firstly look at torch compile right before you write a kernel use torch compile first do not start

learning how to do triton or you know cuda or whatever is your favorite coding language for kernels don't do that instead use torch compile

um even worse like you know this this was RMS norm um you know this is layer norm torch compile wins dramatically um you know versus handwritten kernels. So

I would not you know definitely only use torch compile as your first try. Um do

not write kernels first. Use torch

compile.

So the main takeaway is algorithms are much more important than hardware or whatever handwritten kernels. Right?

Remember deepseek released deep you know deep you know deep spark you know there's other algorithms for speculative decoding like MTP D flash DSpark

whatever all of these are algorithmic improvements and these made inference two times to six times faster right it wasn't like new some new hardware it wasn't some new hardware which made

inference faster it was algorithms which made inference faster right flash attention flash you know FA2 FA3 three, flash attention four, flash attention

five, six, seven, whatever, right? All

of these are algorithmic improvements, right? Flash attention was essentially a

right? Flash attention was essentially a trick to do memory movement much better.

Um, so how do we like orchestrate memory movement and use the caching structure of the GPUs much better? Um, and so flash attention is also a algorithm.

Gradient checkpointing, you know, one of the most important algorithms for training is gradient checkpointing. Um,

and all it does is you do not save all the activations. You do a trick where

the activations. You do a trick where you only save the activations for every single layer. Um, and then you skip all

single layer. Um, and then you skip all the intermediate activations in each layer. Um, and then you recomp compute

layer. Um, and then you recomp compute the activations. Um, and gradient

the activations. Um, and gradient checkpointing saves memory by dramatic amounts by like 70%. Um, 70% memory reduction with no change in accuracy.

And okay, training is a little bit slower maybe by 10% to 15%. Um and you know grading check checkpointing was an algorithm. Um and you know like in

algorithm. Um and you know like in general you should also try to understand you know what is the new data processing tricks you know how do we like you know stagger data you know do

we do do we do curriculum learning or something like that I don't know um what you know how do we clean the data set before we actually pre-train the model there are many tricks you can employ for data processing um and obviously you

know there is still a group of people I don't know I take an opposite view there is a group of people who think mega kernels are the latest and greatest for kernels. You know what is a mega

for kernels. You know what is a mega kernel? A mega kernel is when you take

kernel? A mega kernel is when you take an entire you take an entire implementation of a model and it's just one kernel like one large kernel. Um ah

maybe it's useful who knows um you know you know Nvidia you know Nvidia has a acquired Grock or something um and you know their view is for example you have

two different systems right the LPU which is the Grock system does the decoding right so like the MLP layers the layers does the decoding and then

the GPU so the Nvidia GPUs does the attention and the prefield um and so in general you know we might even have a future We have different types of hardware systems you know we have asex

which are you know specially designed chips for you know computation and we have generalized systems like GPUs. Um

and these asex and GPUs will collaborate with each other. Um so for example the attention you know the the attention will be for the GPUs and they will

transfer over to the LPU to do you know the MLPS and so on. Um and then this is like a dance you know between them and you can also do like pipelining right you can imagine that there's like many

many many replicas of this and they can like you know serve you know 20 people or you know 1,000 people in one go. Um

and yeah so this is like another approach and you know this in my view this is kind of an opposite approach of mega kernels. So as a mega kernel your

mega kernels. So as a mega kernel your view is you want to combine the goal is to make the goal of a mega kernel is to make one kernel for the full forward

path of a language model. Um and once you make one once you once you are able to make the language model the forward path into one kernel you can now make

the entire language model with 32 layers as one kernel. Right? You can extend this and because the whole language model is one kernel you can even further extend it. Right? the prediction of the

extend it. Right? the prediction of the second token, the third token, the fourth token, the sixth token can all be just one kernel. Um, and unfortunately, this is very hard to do. It's very hard

because attention is the problem, right?

Attention has to see the tokens in the future. See the tokens in the past, not

future. See the tokens in the past, not the future. That's cheating. Um, you

the future. That's cheating. Um, you

have to see the tokens in the past. And

that is a fundamental problem. Um and

it's very hard to you know it's very hard to make a mega kernel to combine attention and the MLE or MLP layers.

It's extremely complicated. So in

general what what people do is they will make two kernels right one kernel for the attention part and the other kernel for the rest. Um and so you will see

there are two kernels. Um and yeah so it's very hard to make one mega kernel but you can make two kernels.

Yes. Okay. Any other questions? Any

questions for kernels? So the main takeaway for Yes, a question. Yes, that

is a very good question. So the question was because there's so many knobs for torch compile like 1,00 or something.

How do we reduce the experimentation time to like you know find which knob is the best? Um so luckily we have

the best? Um so luckily we have something called bisection or binary search. That's the trick. So what we'll

search. That's the trick. So what we'll do is instead of checking every single 10,00 combination randomly sample. So

random you do randomize bisection. You

randomly sample 50% of the, you know, flags. You turn it on versus turning it

flags. You turn it on versus turning it off and then benchmark which one is better. And whichever one is better, you

better. And whichever one is better, you then narrow down the search. You again

do 50% and 50% and 50% and 50%. So it's

actually log two of 10,00. I don't know what that what is log 2 of 10,000. I

don't know what that is. Um

two times I don't know. Anyways, log

200. I think you need to do 30 steps, I think. I don't know. I don't remember

think. I don't know. I don't remember whatever 2 to the^ of something is equal to 1,00 then log it. Um so you you only need to do you don't need to do you don't need to check all 1,00 knobs. You

only need to check a few steps and then you will know which flag is the best. Um

so the trick is to use binary search or bisection to do this approach. Um yeah.

Yeah. Any other questions?

Yes.

What are your thoughts on So your question was what do I think about asex like you know cerebras gro sanova I don't know even startups new chips

they do design their own chips I I feel like so the problem of ASEX is is it AS6 or ASX or whatever the problem of specialized chips is the architecture

itself needs to be hardcoded in some of the chips and that is the problem. If you hardcode some of the chips you know hard code the infra

hardcode the architecture labs always like to change the architecture and so every single time when the lab changes the architecture you need to update the

chip. Um but as a GPU the G the trick of

chip. Um but as a GPU the G the trick of GPUs is Nvidia has made it you know Nvidia, AMD, Intel whatever the GPU is extremely powerful because it has

generalized asex inside of the GPU right the GPU is in fact a combination of ASEX. Um and the ASICH is just one large

ASEX. Um and the ASICH is just one large ASICH. Um so I think like in general a

ASICH. Um so I think like in general a GPU is much better because you can customize what goes inside the GPU. you

can disable stuff that goes inside the GPU and such. Yeah. So on so my view is I don't know I don't I don't want to say anything but like in general I don't think

like you know previously as I mentioned you know hardware there is nowhere else to go you know we are at float four unless if the hardware providers invents

float I don't know float zero then maybe we get four you know another four times faster but in general I think I think just people are focused too much on hardware and they have not looked that actually the biggest improvements is not

hardware, it's software, right?

Numerical precision, numerical precision was 32 times faster. Hardware is only three times faster, right? So hardware

only contributed three times faster. Um

oh actually d okay the die size you make the you make the GPU bigger, you get two times faster. That's that's kind of

times faster. That's that's kind of cheating. So I wouldn't really say

cheating. So I wouldn't really say that's improvement. Um but essentially

that's improvement. Um but essentially if you make the hardware faster, you only get three times faster. Um so in my view hardware is probably overblown. you

know hardware is actually not that important. The software was the trick

important. The software was the trick that Nvidia, you know, Nvidia, AMD, Intel, all of these, you know, hardware providers, they banked on the fact that numerical precision was a trick and

tensor, tensor, numerical precision, sparsity, you know, these software tricks. Um, okay. Well, tensor is not

tricks. Um, okay. Well, tensor is not really software trick, but you know, a tensor is kind of an ASICH inside of the GPU. Um, and so like I feel like that's

GPU. Um, and so like I feel like that's Yeah. So my view is I don't I don't

Yeah. So my view is I don't I don't really see a future for ASEX. That's my

view. Um I think that ASEX are like instead, you know, to be honest, I'm actually quite surprised. We have lots of asset

quite surprised. We have lots of asset companies, but we have very few algorithm companies. Um and the reason

algorithm companies. Um and the reason why is because ASEX you can sell, right?

Every single year you can upgrade. You

know, this year you pay $1,000 to ASICH version one and the next year you have to upgrade, right? The problem with algorithms is algorithms is very hard to

you know force the user or whatever to pay again and so that is why hardware is very popular because hardware is a very easy business model but for algorithms it gets more complicated right how are we going to monetize grading

checkpointing I don't know right that's very hard um so but the main point is the large labs themselves I think like open air announced collaboration broadcom and suras whatever you know

each lab themselves are going to the hardware provider and designing the chip with them. Um, so my view is like maybe

with them. Um, so my view is like maybe we'll have more of these like collaboration approaches, but I feel like standalone standalone assets, I don't think they're going to last. Um,

yeah, that's my take, I guess. Any other

questions? Yes.

Oh, you mean what are the types of kernels or Oh, okay. Okay. Okay. Um, so the

Oh, okay. Okay. Okay. Um, so the question was what are the you know what are the changes for kernels or optimizations or stuff that is like interesting I guess for kernels. Um so

most kernels when you write kernels the majority of them are are focused on memory movement reduction. How do we reduce memory movement? That's the

majority of kernels. Um for example there's there's a trick called um you know there's a trick called fuse cross entropy loss where instead of making instead of the last layer of cont

instead of materializing the full logs there is a trick you can do it in batches right you can do rowby row materialization. Um and so this will

materialization. Um and so this will reduce memory by like a lot by like I don't know 10 GB or something if you have long context or even more. Um

that's one way. Um the other kernels most kernels are called kernel fusion where you you have this like long pietorch function and all you do is you just write one

kernel to do this whole pietorch function and torch compile will do this for you. So torch compile is very very

for you. So torch compile is very very good at doing kernel fusion right you give torch compile a function it will write a kernel a try kernel or whatever kernel and it will just fuse everything

um it's very very effective for that um but I think in general kernels are just reducing memory movement um and so like I you know to be honest I don't really

like to call it kernels most algorithms so most algorithms you either make training faster or reduce memory usage um but kernels in my view kernels is

reduce memory movement. Um, and so most kernels is just memory movement, you know, memory movement optimization, right? How do we how do we use the

right? How do we how do we use the caching structure of the GPUs? Um, you

know, how do we not load the same variable twice or three times or whatever? Um, yeah, I'm not sure if that

whatever? Um, yeah, I'm not sure if that answer your question, but next reinforcement learning. Um, and after

reinforcement learning. Um, and after this will be reward hacking the agents.

Um, so as a primer to I'm assuming most people know, do most people know reinforcement learning or do I need to prime people? Okay, I'll give a very

prime people? Okay, I'll give a very fast primer for reinforcement learning.

Okay, fast primer for reinforcement learning. Um, what is reinforcement

learning. Um, what is reinforcement learning? You have this environment such

learning? You have this environment such as this Pac-Man game. Um, and your goal is as the player, you know, to maximize reward. You want to eat all of the

reward. You want to eat all of the cookies, right? You want to eat all of

cookies, right? You want to eat all of the cookies, but also escape away from your the monsters. I don't actually know what they're called. Enemies, monsters,

whatever, whatever they're called. Um,

and your goal as Pac-Man is you want to maximize the amount of cookies that you eat. Um, and that is your reward. The

eat. Um, and that is your reward. The

reward is the cookies. Um, and the action is whether you go up, left, down, or right. Um, and the environment is the

or right. Um, and the environment is the game. Another good example, you know,

game. Another good example, you know, another way I like to explain reinforcement learning is the goal of reinforcement learning is you want to have more good and less bad um during

training. Um so for example, at the very

training. Um so for example, at the very beginning of training, you ask the model what is 2 plus two? Um the answer is clearly four. Um but when the model

clearly four. Um but when the model starts training, it will be very dumb.

It will be very bad. it will see B, you know, the model would just say B, D, cat, dog, house, mouse, whatever. Um,

and the trick is for all of the bad responses, you want to decrease, you don't want you want to like negatively reward this or penalize it. You want to penalize the model if it says something

bad and you want to increase the reward if it says the correct answer. Um, so

that is the trick of reinforcement learning. You just want more good

learning. You just want more good answers, less bad answers. Um, and if it's like, you know, very close to the correct answer. So, you know, three is

correct answer. So, you know, three is very close to the correct answer. Um,

you want to reward, you want to negatively reward this a little bit less, right? Because three is much

less, right? Because three is much closer to four than B or D. Um, so if you do B or D, you want to negatively reward it massively.

In reinforcement learning, the trick is you have a verification system, right?

You have a verifier to verify if the model is doing good or bad. Um so you'll call the model many many many times. Um

and each of these examples you give a verification number right? So for

example um the first example is very good so you give it a plus 10 score. Um

the next example is like okay so you give it a minus5 score. Um and then the last example is very bad so you give it a minus 100 score. Um and reinforcement

learning allows you to assign scores to each of those answers and questions. Um

and so that's kind of reinforcement learning verifies. Um and the trick of

learning verifies. Um and the trick of reinforcement learning is my favorite phrase is patience is all you need. Um

at the very beginning of training your model will do very bad, right? Your your

reward will be 0000 you know 0000. You wait for a very long time and then you will get the correct answer. Right? So for example this

answer. Right? So for example this example you ask the model what is 2 plus2 right? You start pre-training the

plus2 right? You start pre-training the model. you start pre-training the model,

model. you start pre-training the model, the model doesn't know what is two plus two, but after 10 years it will say four. Um, okay, obviously not 10 years,

four. Um, okay, obviously not 10 years, I'm just exaggerating. But after 10 years, you wait 10 years, the model will then say four. Um, and

that is why my favorite phrase is luck is all you need for reinforcement learning. You know, maybe by chance you

learning. You know, maybe by chance you will get four very quickly. Um but you know maybe you just have to wait and wait and wait and wait for eternity until reinforcement learning works. Um

and so in general your reward will be zero for a very long time and then you will get you know you will increase reward um after the zero

and you know for reinforcement learning there is a very simple algorithm for reinforcement learning and the trick of reinforcement learning is remember you know the final answer you want to you

for example you know what is 2 plus two you know the answer is four but the problem is you don't know what is the reasoning trace, you know, did was the reasoning trace good or bad? So, for

example, this example is, you know, to tell the model to create a fast matrix multiplication algorithm. Um, and the

multiplication algorithm. Um, and the trick is if the answer is right, you reward every single line as plus 10

score. Um, and if it's wrong, you reward

score. Um, and if it's wrong, you reward every single score as minus 100. Um, and

you know, Andre said, you know, in a Darkash podcast, reinforcement learning is kind of like sucking supervision bits through a straw. um you know we actually have stickers for them if you like. Um

so you can get one of your stickers which we can distribute at the end. Um

so Audrey's quote is this um you know and the main point is reinforcement learning is terrible but everything else is even worse. Um and so like you know reinforcement learning is the only tool

we currently have that just works. It

works but it's not very efficient. Um

and okay actually okay that's the next section. Um but the main point is okay

section. Um but the main point is okay that's a reinforcement learning primer.

Um I guess does anyone have questions on reinforcement learning primer?

No.

Okay, I'll skip to Okay, one question.

Yes.

I will mention that in the next section.

Um there is there is like you know better RL methods. Um but in general reinforcement learning seems to do very well for now. Last I think this is the last topic or maybe not. Reward hacking

and agents.

The most fun one I guess. Um so okay for reinforcement learning reinforcement learning can only work if the probability of a good answer is more

than zero. If it is less than zero

than zero. If it is less than zero reinforcement learning will never work.

So that is a fun that is a constraint of reinforcement learning. The probability

reinforcement learning. The probability of a good answer must be more than zero.

It can never be zero. Um and there are many many many problems of reinforcement learning not working. You know the formatting could be wrong. you know, you need to do some sort of priming or warm

up. So, you have to do like some sort of

up. So, you have to do like some sort of trick to teach the model a little bit about, you know, about the thing that you're trying to maximize. Um, you have to do supervised finetuning. So, one of

the tricks of reinforcement learning is you actually need to do SFT or fine-tuning to make the model not dumb, right? To make the probability of zero

right? To make the probability of zero not zero, the probability of a good answer not zero. Um, you need to do good pre-training. Um and then the other

pre-training. Um and then the other problem is that you know during reinforcement learning it's just way too out of distribution that reinforcement learning is just very bad. Um so there are many many problems of reinforcement

learning and I think we just you know for the trajectories reinforcement learning can assign incorrect rewards to the trajectory right remember the simple

trick of reinforcement learning is we assign the reward to every single line as the same number right either this is good or this is bad and this is not good

because why right you ask the model I need to find what is 2 plus two the answer is correct Right? The answer is four. The model says it's four. So you

four. The model says it's four. So you

reward this whole thinking trace as plus 10. But this is wrong because as you can

10. But this is wrong because as you can see in the thinking trace it says 2 plus 2 is equal to 10.

Imagine you know in all of training because the trick of reinforcement learning is we just literally assign 10 to every single line or minus 100 to every single line. We missed this bad

you know bad thing. Um so you can imagine when we keep training the model the model might hack or do reward hacking or you know make gibberish it

will do gibberish in between do some do some sort of like new machine language which we can't read and it will assign high score to that. Um and so this is a very big problem of reinforcement

learning and the way to solve this or fix this is something called process supervision. Um

and process supervision what you do is you manually check every single line not you don't just assign plus 10 to the final you know the answer is correct right the answer is correct plus 10

assign every single line as plus 10 you don't do this instead what you do is you assign every single line as a different number right you assign some lines as

plus 30 some lines is plus zero whatever the bad lines is minus 100 right this works very very well um unfortunately

process vision cannot scale and it's extremely expensive to do right who's going to label this it's the you know the humans I guess right we have to

label this data right we have to manually label for the labs I guess that's why labs sometimes like you know they go to scale call whatever right they ask people to label the data you

know is this good is this bad is this good is this bad um and so on um but the trick is you can also use a language model, right? You can use LLM as a

model, right? You can use LLM as a judge. You can you can call a language

judge. You can you can call a language model to label every single line. And

you know, my view is like, you know, large labs are going to be doing this process more. They will call their own

process more. They will call their own model iteratively to re-review itself.

Um, and that is one way their view is they can reach AGI, right? Just by by re-reviewing itself, right?

re-evaluating itself, re-checking, doing doing you know automatic LLM as a judge process supervision something like this.

Um but remember there is a problem because even if you do process supervision the model you are using the same model to evaluate the model right the same

problem as we bench pro right su bench pro you use the LLM as a verifier to verify the LLM which is definitely not good um and the reason why is because you can do reward hacking

um a very good example of reward hacking is your model starts cheating um so for example when you want to make a fast matrix multiplication algorithm. All it

does is it deletes the timer. Um right

remember you give the goal to max to reduce the time. Right? Reduce the time of the matrix multiplication algorithm.

Um so all it will do is just delete the timer. Let's delete the timer. Set the

timer. Let's delete the timer. Set the

timer to be zero and then there we maximize a reward. Um obviously this is not correct, right? Because the trick is you also have a correctness check, right? You check if the matrix

right? You check if the matrix multiplication is actually correct. Um

but there is another way the model will edit your two matrices to be just zero.

Um and what is 0 time 0? Zero. Um and so the correctness checks also fail. Um and

so reward hacking becomes a very very big problem because these models can cheat and do special tricks to go around your actual model um your intent of the

reward function.

Another very problematic example is it's not just about reward hacking. It can

actually destroy your computer. Right?

By bad luck your model might output you know some sort of corruption methodology you know deleting you know doing rm-rf on your entire computer and bye-bye your computer's dead. Um and so like you know

computer's dead. Um and so like you know sometimes this also does happen. Um so

it's not just reward hacking also trust of your tool cause you know trust of whether the model is actually doing good or bad is also a very big problem and remember this plot that I showed you

know if you include GPD 5.6 cheating on the benchmarks you know looking at the answer you know remember the previously su bench uh bench pro and deep show that models also cheat by looking at the

final answer you know you can see that with GBD 5.6 If you cheat, it does very well. But if you remove the cheating

well. But if you remove the cheating examples, it does, you know, within trend.

And then, you know, maybe you might be thinking, oh, this reward hacking thing is like, oh, it's like very rare, you know, very rare. It's not going to happen in real world. Um, well, GLM 5.2

during its training methodology, they specifically mentioned they have this new methodology for reinforcement learning called anti-hacking. Um, so GLM 5.2 introduced a method to stop, you

know, reward hacking. Um and what they do is they added a link checker. Um so

remember previously we mentioned how SweetBench Pro um the model will cheat and look at the answer. Um and so what GLM did is they had this check. Um so

during reinforcement learning they will check every single tool call you make.

Um and if the website if the website went to the answer you would stop that from happening. Um and so like GLM

from happening. Um and so like GLM essentially outed this like you know filtering system for the entire reinforcement learning process. Um and

you know according to them it worked very well and remember this plot about cheating examples. Um you know opus it seems like

examples. Um you know opus it seems like claude's models like to always cheat. Um

and Jubet's models don't like to cheat.

Um but the main takeaway is models will cheat because you are you are telling it you know like you know I want to maximize reward AB CDE EFG. Um and so

the model will it will maximize it but it won't actually follow your intent. Um

so you have to be very careful on this.

Um in fact for GBD 5.1 during its training OpenAI mentioned that they had something called calculator hacking. Um

and so in GBD 5.1 when they were training um they wanted to reward web tool use right so like you want to reward the model to use the web tool. Um

but instead it didn't use the web tool it used the calculator to fake the web tool. Um and so during the training of

tool. Um and so during the training of GBD 5.1 this happened. Um and so like you know there's many many many many problems. I think they show yeah they showed calculator hacking. You know you

lie about which tool you used. Um you

know you conceal uncertainty you make facts up. Um so there's many many many

facts up. Um so there's many many many problems with um reward hacking. And

this is not fake right? So reward

hacking is already in large labs training runs right? This is just 5.1.

Um I don't think so they mentioned GB 5.2 or whatever. Yeah, but in general they showed that you know this thing does happen in real world um you know I don't know if you guys know GPU mode um

but GPU mode does you know this leaderboard um for you know making faster kernels so if you do want to write your own kernels definitely post on GPU modes hackathon challenges um they're very very helpful and very

useful um but you know someone managed to hack reward hack the GPU mode kernel competition um and remember in the

Matrix multiplication example. There are

two there are two there are two checks that we need to do right make the matrix multiplication algorithm faster but also it needs to be correct right there are

two checks the correctness check and the timing check. Um and GPU mode also had

timing check. Um and GPU mode also had two checks the correctness check and the timing check. Um and so what do you

timing check. Um and so what do you think the model did when the model the model knew the model actually knew that it was being evaluated on the correctness check right it learned oh

I'm being evaluated on the correctness check I will now make correctness correct right so it will output the correct kernel and then the model knew

that it was getting timed and what it what did it do it just it just did the algorithm once and then saved it and it skipped all the another 15 um you know

tests. Um and so that's what the model

tests. Um and so that's what the model did. So essentially the model learned

did. So essentially the model learned the model learned that there were two tests, the correctness check and the timing check. And the model only did the

timing check. And the model only did the correctness check correctly and then once it went into the regime of timing, it cheated. Um to be honest, it's

it cheated. Um to be honest, it's actually quite scary. So essentially the model learned that you're doing these tests and the model actually knows you're doing the benchmarks. Um and so this is actually very interesting. Um

and you know, oh yeah, this is this is more an you know, larger example. The

correctness check was fine, but the timing check it cheated. Um and all it did is it launch, you know, there was supposed to be 15 calls in the first call. In the first core, it did all 15

call. In the first core, it did all 15 of the entire process, right? It did all of the 15 runs. Um and then core two to 15, it just did a Python dictionary look up. Um, yeah.

up. Um, yeah.

I don't know if you know about this.

Reminds me of Volkswagen where they initi.

Yes, I someone did tell someone told me about it. Um,

this is very similar. It's like, oh, I'm not doing this. Turn this off and Yeah, exactly. So, like, you know, it's

Yeah, exactly. So, like, you know, it's not just models, I guess, that cheat.

Even humans cheat, I guess. Yes. But I

think it's called Goodart's law. That's

the one. Like, if you have a benchmark, then the benchmark becomes Is it good law? I don't remember. Yes. Okay. Yeah.

law? I don't remember. Yes. Okay. Yeah.

The benchmark essentially becomes useless because people just cheat to maximize reward. Um yes, I guess humans

maximize reward. Um yes, I guess humans also cheat. Um yeah. Okay. Oh, my

also cheat. Um yeah. Okay. Oh, my

favorite example is um so on other labs, you know, you see on Twitter, on wherever, they say they made kernels 10 times faster. Um

times faster. Um no, no, no, that's not correct. They did

not make kernels 10 times faster. In

fact, if you look through the code, they have no, you know, no ops, so no operations. They also edit the timer.

operations. They also edit the timer.

You know, they, as I literally described, you know, I described, they, you know, over here, um, you know, they edit the timer, they made matrices go to

zero, they cheated. Um, and so like, you know, this actually happened in real world. So some, you know, some of the

world. So some, you know, some of the labs, they published papers claiming that they made kernels 10 times faster.

But actually if you read through the code and the examples they these examples all cheated. Um and so you know they you know this is not very good in terms of you know reward hacking. You

know reward hacking is a very big problem. Um and you know for example

problem. Um and you know for example what some of the examples of kernel reward hacking you know not generating real CUDA code instead it cause or some sort of like you know already written

system. um you have no up kernels which

system. um you have no up kernels which is essentially making the you know making the A and B matrix just zero. All

it does is just doesn't do anything, right? It just the kernel is empty. Um,

right? It just the kernel is empty. Um,

and you have like memory reuse, so you reuse the same answer over and over again. Um, you have timing

again. Um, you have timing synchronization issues. So that's

synchronization issues. So that's cheating on the timer. Um and my view is like you know if you do publish faster kernels or faster you know matrix if you

think that your AI agent has made kernels 10 times faster please verify you know please look through the code before publishing because it is a very

it's not a very good look um and so and also the biggest issue that I feel like people are getting forgetting is you know you made kernels 10 times faster

you made matrix multiplication 10 times faster There is a theoretical limit for matrix multiplication, right? Matrix

multiplication, right? Matrix multiplication, you know, it's not you can't make a faster because there's mathematical limits on how to make a faster, right? And so like, you know,

faster, right? And so like, you know, matrix multiplication at the very very very olden times, you know, it's O of N cubed. You know, every single time

cubed. You know, every single time researchers have make it faster and faster and faster and faster and faster.

You know, it's now O of N to the^ of 2.371339, I guess. you know researchers every

I guess. you know researchers every single year are trying to like make this number smaller and smaller and smaller and smaller. Um you know I guess like

and smaller. Um you know I guess like you know 1 1552 to 1339 is not that small you know not that big I guess. Um

but you know they're having progress but the main point is you know these researchers you know they show with mathematical limits you cannot go faster than this and so how can you do reward

hacking that is even faster than that.

Um and so like the fundamental point is please verify you know to like the people who do research papers and stuff like that please confirm your model is not reward hacking. It is a very big big

big problem. Um and you can see oh I

big problem. Um and you can see oh I think I only had one plot. Um but yes in general please do not do please check your I guess models. Um I guess that's

all for the talk. Um you know yeah thank you everyone for coming. Oh more

questions as well. Um okay thank you.

Thank you. We also have Oh, yes. We have a whole bunch of

Oh, yes. We have a whole bunch of stickers that you can take in the box over there and some pins and stuff.