OpenAI's Yann Dubois: Why AI Progress Suddenly Feels Real

29:42World models in the sense that, yes, you can try to replicate or simulate things, like basically work in an environment that is simulated yes the problem is simulations are always going to be really hard and not going to be truthful so I think there will always need to be a certain little bit of training that will need to happen in the real world to make sure that the model realizes these mismatches between the simulated world and the real world and I think we as a field have a tendency of optimizing something that is simulated or not quite realistic past the point where this is useful. So that's something that I think we should always be careful with is we spend a lot of time and effort on optimizing something simulated or not quite realistic, and it's great at the beginning, but at some point once you start optimizing too much for something, it's not representative of the real world, and people continue doing that just because that's what they've been doing for a long time.

30:49So I just think people need to realize when to stop that. I don't work with this type of synthetic environment as much, just because I don't work on embodied AI. So I don't know if we heard that yet. Okay, great. All right, so going back to pre-training, mid-training, post-training, let's talk about mid-training. It's maybe something that people have heard about a bit less. The term comes up a bit less. What is it and why is it important? Mid-training is just this idea of something that's between pre-training, as you might realize from the name, and kind of the post-training part of the pipeline.

31:29And really, the idea is if you have high-quality data that is more representative of what you really want in your final model, you should overtrain on that data. so taking a step back here pre-training, what is it? pre-training, it's basically trying to learn everything from the world by learning everything from internet at a high level the problem is that most things on internet are not really useful if you think for example about Wikipedia or like GitHub which is like coding data it just seems like there's way more information in there than some random forums yeah some random farms that maybe not have that much information.

32:17For example, ads. There's also lots of ads on the internet. You probably don't want to train too much on that. But in pre-training, we train on everything. And in mid-training, we basically overweight this type of high-quality data that we think is more useful for training the final model. And this is something I can't talk about what is happening at OpenAI, but it's something that is happening definitely in all the academic community right now and in all the open-source models have this stage of mid-training. Great. Post-training, let's start at a high level by defining what that is. So there's reinforcement learning, but that's not the only part of post-training.

32:51What else is there? It kind of depends how you define the term and where you put the boundaries. In my mind, post-training, including, I'll take it from a very broad sense, which includes all the reinforcement learning and the training for our reasoning models. It's just the idea of having something that knows everything about the world to making something that is useful to people um so pre-training i think about it or the metaphor that i like giving is uh you go in the library and you have a lot of books about everything and in theory you can find all the information that you want in the library but it's much more useful to talk to an expert who has learned these books and that you can ask questions to and they can answer they can answer and like they can understand what you're actually looking for.

33:40So this is kind of the goal of post-training at a very high level, is making something that is useful to users and is easier to interact with. So there are multiple stages. I'll talk mostly, well, I'll talk only about things that are happening outside of OpenAI and kind of the usual stages. There's usually some SFT that is happening. Which is supervised fine-tuning. Supervised fine-tuning, yes. Supervised fine-tuning. And that's actually what, early on, most of the models that we're portraying were only doing supervised fine-tuning. The idea is that if you have humans that can give you the desired final answer, so if you have humans that can give you the gold answer, you can basically clone the behavior of the human.

34:34So this is what we call behavior cloning. The problem with this is that you will never get better than what your ground truth gives you. And humans are actually pretty limited in many sense. So you will never overcome the human labelers that you're working with. The reinforcement learning stage goes from behavior cloning to really optimizing rewards. So the idea is, I don't know what the ground truth is. I don't know what the perfect answer is. But here's how I would say whether the answer is correct or not. And here are the things that I want in the answer. And what you do is you start optimizing, you start having a model that tries to get more reward, basically optimize more this reward function.

35:23That's how we call it. And it goes beyond what you currently have, what humans can do, or at least the humans that you're working with can do. So this, I would say, is the two big stages. Then in reinforcement learning, that depends on which models are being trained. At least in the open source community, it seems that there are different ways of doing that. Reinforcement learning when you have very fireball rewards. So reinforcement learning where it's really easy to say whether something is correct or not, and you can really kind of have a binary reward for this. And that goes back to how we talked about a one and a one preview in the past.

36:02and then you have reinforcement learning without verifiable rewards where maybe I could do pairwise comparisons I can say this answer is better than this other one but I don't really know I cannot quite say this is the perfect answer so of course it's a continuum and there's everything in between but I would say these are the three high level things to think about when you think about post training in general and how people are usually doing it in the open source world is that they take SFT, they clone the behavior that you can collect online or from humans. And then once it's already at a pretty good level, they just do this reinforcement to go beyond what we currently have.

36:47Because if you just started from reinforcement learning, it would be very inefficient. Because the problem with reinforcement learning is that you have to stumble across the right answer, basically. Because how reinforcement learning works is you sample many times, essentially, from the model that you're training. And you say, this one is correct. This one is not. And you say, do more of the one that is correct. So you have to stumble across the right solution. So you're much better off first getting as much, as close as possible to the best you can do. And this is this behavior cloning and then doing reinforcement.

37:20Does reinforcement learning create new capabilities or does it make the model better at existing capabilities? It's really hard to say because pre-training, what is trained on all of the internet, arguably already has all capabilities in it. So it would be even hard to answer this question scientifically because arguably everything is already there. What I would say is that if you look at models that we were training or that we were post-training like two years ago in the open source world, for example, I worked on one of them, Alpaca, where we used 50 ,000 examples for SFT. And like now when you look at reinforcement learning from models like Kimi or from DeepSeek models, it seems that they are closer to 1 million data points.

38:14So definitely people scaled up a lot the reinforcement learning stage. and from this it seems that they've learned like new capability like this reasoning aspect, this fact that you can check your answer and try to improve it. So you can really think for longer to get a more correct answer. So all this to say that arguably everything is already in pre-training but we were definitely able in the last one year and a half even in the open source world to have more capabilities after reinforcement than we used to before. I heard several times that reinforcement learning is pretty finicky and hard to scale.

38:59And part of the reason why we, as an industry, didn't do reinforcement learning as part of the initial kind of LLM sort of progress curve was precisely that, that it was hard to make work. What is hard about scaling RL? Is that a question of data sets, knowing where the rewards are, or something else? I would say most people who did not work in reinforcement learning in the academic and research community up to two years ago probably thought reinforcement learning just doesn't work and is too finicky to work with. I used to be that type of person. And actually, when I saw ChatGPT come out, they had this blog.

39:38I was not at OpenAI at the time. I saw this blog that says that they use reinforcement learning. And my first thought was, I can do the same without reinforcement learning. Because this is just an overcomplicated method. And this is actually the product that we started working on with Alpaca, was exactly, let's try to reproduce that only using SFT, just by doing this behavior cloning. Yeah, and like, for example, Yann Lequin famously gives this metaphor of, oh, the reinforcement learning is just like the cherry on the top. So I think that was really the intuition that most people had. it seems that after crossing a certain scale of models that know basically everything about the world and what we call like good priors about the world it seems that reinforcement learning just started to work and this is not only with LMS robotics seems to have or it seems to be entering the same stage where they're realizing that actually it used to be very finicky but now that we use models that like know already everything about the world it actually learns pretty well.

40:37Now to answer your question about what is still complicated with reinforcement learning, one is an infra aspect. So just like systems in general, reinforcement learning, you have at a very high level, basically to sample, as I said before, many answers and say what is correct and what is not. And this sampling is just very expensive and you have to do it at scale. The other issue that also in the open source world people are seeing right now is that when we are training more agentic systems, you only know whether you're correct at the end of your very long rollout. So you get very little information per token of whether you were correct or not.

41:30And it's hard to say, it's hard to basically do attribution. It's hard to say what part of your entire answer was the one that led you to being correct. So that's more of an issue on the machine learning side. The ideal world in machine learning is when I can say exactly like this thing was good, do more of that. And the problem again with these agentic systems and reinforcement agentic systems that you don't really know which part was good or not until you arrive at the end. That's another big issue for reinforcement learning. What's the current frontier of reinforcement learning? It seems like there's a jungle of acronyms like GRPO and other techniques.

42:12What are you using? What are you excited about? What do you think is promising? So I can't talk about what we're using, but for example, in the open source world, GRPO seems to be working very well. And people used to have different methods like PPO and DPO, and people seem to have really converged to this one. The big difference with other methods is that you, again, you do this simple method that I told you about sampling as many answers as possible, and you say which one is correct. So in some way, GRPO is a very simplistic method. And in general, we saw over and over again in machine learning that the simplest method where you can scale up in terms of compute usually is the one that ends up working the best.

43:03And that is kind of what is happening here, at least in the open source world. As you describe some of the challenges, question crossed my mind. You know, you often hear that AI systems are not built, they're grown. How are you characterizing it as well? What part is science versus a craft or trying multiple things? than just keeping what works best in your day-to-day life? Yeah, that's a great question. I think how it usually works is that it starts being craft. People just try out many things and they start building a mental model of what works and what doesn't. And over time, we move from this craft land to more science.

43:47Science is... or like more scientific approach are really the ones that like first end up working. It's hard. It's very rare that you take a really scientific approach and you say like this is the optimal thing to do and you do it and it just works. Like people just there's some sense of alchemy. People just have like a good flair for something and they make it work. And then other people or that person starts trying to improve what we are doing by being very scientific. And I would say this happens over and over in machine learning. So first craft, then science, and both are really important, but it's different stages of the pipeline.

44:35In terms of engineering, this is definitely something that is always necessary. so I would say most researchers have moved to being relatively good at like at least I wouldn't say good engineers but good at working in like complex systems and like figuring out what they need to try out and the systems and the infra that we have has become more and more complicated so definitely the work required changed over time Fascinating. All right. So still in reinforcement learning and circling back to some of the things you said at the beginning. So if I want to make my model better at computer use or genetic coding or whatever domain, then I would spend a particular amount of time doing specifically reinforcement learning for computer use and putting together a data set and then coming up with rewards.

45:35Is that how it works? Like you just pick one problem and you just do reinforcement learning specifically for it? To be clear, I talk more about reinforcement learning because also this is like the part I know the best. And this is what I've worked, like pushing I've worked on for a long time. We talked about mid-training before. Like all these things are also extremely important and you can improve it in different parts of the pipeline. As I said before, the closer you are from the final stage of the model, usually the smaller the scale of the training becomes. So you can iterate fast on that because now you can iterate in terms of days rather than iterate in terms of months.

46:17So usually people start from this fast iteration loop and then they go deeper and they make bigger changes across the entire stack. So this is not to say that only reinforcement learning matters. I'm really not saying that. but it's just like that's why people will start doing changes and then that will permeate and we will go deeper into the stack. So this is how it works. And like in the open source world, it's very much like that too. I think you see way more post-trained models than you see new pre-trained bases. And you see way more like improvements in like the algorithm and that's why we talked about, I mean, GRPO, DPO, BPO, like there are so many XPOs And that's because people can iterate really quickly on this final stage of the pipeline.

47:06And the jagged nature of those models, does that come from this approach of picking this problem and that problem? And therefore, it's going to be excellent that those problems are not as good as other problems? Or is that a more fundamental characteristic of AI models? There's definitely some of that. for sure if you optimize more on specific types of problems, you will be better in that setting. I would say, this is my intuition, is that it's less about the exact problems that you're optimizing on, and it's more about the class of problems that you're optimizing on. So for example, if you are really good at math competitions, your model will probably be pretty good at coding competitions.

47:53So it's not about the domain. It's more about the skills that are necessary and the way to think and this horizontal capabilities that you need for performing these tasks. And that's what I think you're usually seeing when someone is really bad at something, it's actually bad at that in any domain, in any language. So you have to think about this domain and then this generalization of this domain, not necessarily per domain capability. So speaking of generalization, So there's been that clear evolution from math and coding success to now starting to cover different areas. So that's the whole GDP valve thing where like across the economy, different areas are being evaluated in terms of like model performance.

48:41It's sort of the same question. Is that the result of overall model progress or is that deliberate? it. Okay, now we're going to take this part of the economy and build a data set for it and do mid-training and do post-training. How does that progress work from those very specific domains to generalizing to the rest of the world? It's definitely something that we actively push on. I think people are realizing, I mean us and also other companies, that we are moving towards this world where we want to really make products that are useful and like improve like productivity of people um and and help people in the day-to-day life so i think there's a there's a very active move to deciding what are the domains that we should be prioritizing what are um now that we know we have an algorithm that we can apply in different places uh what we are constrained by is more collecting the right data having people who really care about a certain problem work on that problem.

49:49But there are not that many people who can do these things. So you really need to prioritize. So this is, yeah, it's a very active, it's a very active, proactive kind of approach here. And in general, I would say the performance of the model really depends on like the number of people who care about the final output of the model who are looking at that model. So if they start looking more on specific verticals, like these verticals will improve really quickly. But again, we don't have that many of these people that can do these things. But to unpack something that you alluded to, I think a minute ago, do models actually generalize now more, especially from a reinforcement learning perspective?

50:38So making a model very good at domain A or B then is likely to make the model better at C, regardless of the amount of effort you put into developing rewards for domain C? So I think there are different axes of generalization. One, there's an algorithmic generalization. And that's like really, can I use the algorithm that I developed or this black box that I developed for domain A, and can I use it for domain B? and at least again like even talking about the open source wall it's really seems that like people are able to do that they take grpo they apply it in like many different places and it just works so that generalization seems to be relatively good which which is why we're seeing a lot of progress otherwise it would be hard to make progress then there's the generalization of the model that is trained on one particular data set and this is what i was alluding to before is at least my mental model is that generalization happens in terms of capability.

51:41Like if the capability is the same, you will see generalization across domains. Again, like different languages, like coding, like you can optimize for C++ coding, for having a good C++ model with very little training on C++. Partly because this pre-trained model, or very little RL in C++, partly because this pre-trained model has seen all of C++. And so it already kind of like understands the basics of that language. So that type of generalization definitely happens. The generalization that I think is harder are these, when we don't have these like horizontal capabilities. So I'll give you one concrete example.

52:26If my model is very intelligent in terms of being correct on like competitions, I usually take that example because it's like somewhat constrived at like math competitions, like coding competitions. From a human perspective, people that are good at these things are usually just smart. And if they are smart, or like someone might think that at least, that they are just smart. And if they are smart, they can actually do other things too. But that is really not true. And that type of generalization is really not true because many things where we need to have humans working on like expert domains, like the world is very messy.

53:00and these coding competitions and math competitions are extremely well-specified. And you need to have the capability of understanding underspecified tasks, understanding how to deal with the messy world and understanding what are even the resources that you need to answer the question. If you look at the math competition, you usually have everything in the prompt. It's like you have five lines or maybe 15 lines and it's like all the information that you need to answer this question. In the real world, if I'm a consultant, if I work in like finance, I need to go on the internet. I need to like find and extract different information just to understand before doing any of the reasoning, just to be able to do that reasoning.

53:47And this type of like horizontal capability is the thing that doesn't usually, like you generalize if you have that horizontal capability, but in many cases we don't have that horizontal capability. so yeah that's why we hallucinate actually in every domain like when you have hallucination of lms if if a model is really bad at saying that it doesn't know that usually happens in every single domain you won't have like one domain where the model is extremely calibrated about its knowledge and another domain where it's not and as a quick day tour is uh is is hallucination also a reinforcement learning problem where you reward the behavior to say i don't know when it occurs?

54:29John Schulman has a great presentation about that, I think from like one or two years ago, where he was saying that if you do behavior cloning, so this like SFT that we talked about before, you will basically reward and optimize for hallucination because what will happen, or you could optimize for hallucination because what will happen is if your model doesn't know about something, but now you say that the right answer is to say that something. So I'll be very concrete. If the model doesn't know about a paper, and now in an answer that you give, that is given by a ground truth answer given by a human, you say, here's where I got the information, and then you cite that paper.

55:13Like what you're actually optimizing the model to do is citing something that doesn't exist because it doesn't know that that paper exists. And so John Solomon had this great presentation saying like SFT is going to force like a hallucination while in reinforcement learning, given that, as I said, you kind of sample from the model in the first place, extremely unlikely that you sample something that it doesn't know and it's correct. That's like extremely unlikely. So you will never reward that behavior. You will only sample things that it doesn't know and being incorrect and then you will kill that behavior.

55:49So hallucination, at least the intuition that people have is that it can come, for example, from SFT and it can come from this like porturing pipeline. But if you have good reinforcement in pipeline, that shouldn't happen too often. And going back to generalization as well, are there examples where actually getting better at one domain makes the model worse at the rest? A little bit to what you were saying about like some people are very good at math, some people are very good at English. Pretty often they're not the same people. in domains usually not what will happen though is um you will make decisions based on which domain we optimize for and if you optimize for one domain you will be able to optimize less for another one so it's not necessarily that optimizing for one thing will make the other one worse it's just that as a result you can optimize less for the other one because your compute constraint your data constraint, you have like your human bottleneck also in terms of that work.

56:53What does happen is you can have negative kind of generalization, like bad generalization, or negative transfer more for these horizontal aspects of the model. So I'll give you a very concrete example. Explicit instruction following versus implicit instruction following. If I have a model, And this is, we often hear, for example, from OpenAI models that they tend to be really good if you tell them exactly what you want. But as a result, sometimes we hear also that they're like less good if you are not as specific about what you wanted. For example, if I make a typo and I say like change this file and I make a typo in this file, an extremely good model at explicit instruction following will change the wrong file, the one that has a typo.

57:47But humans would probably realize that you made a typo. And as a result, there are cases where this explicit instruction following goes against this implicit instruction following. So you will have cases where basically these horizontal capabilities go against each other. And maybe to close on this whole reinforcement learning conversation. So is your sense that as we progress from being excellent at coding and excellent at math and move to the rest of the economy, do you think that the rest of the economy is a tractable problem? Do you think we can get to the same level of performance ultimately?

58:27Yes, but I was like, yes, we can. I don't think there's anything like really deeply special about these domains where we cannot optimize and where we can get the same with other domains. The bad is for at least two reasons. The first one is most of the people working on these models are pretty good at coding and they really care about coding because that's what they use as the each day kind of drivers. and there's nothing better than the user being also the one who like trains the model because like then they understand the issues it's um it's very hard to really like for me for example it's very hard to really understand like what should we change on the like on like legal uh aspects of the model if i don't understand anything about the legal domain um so that's one thing The other thing that you will often hear about, and I mentioned also briefly about before, is this kind of verifiable rewards.

59:26There are domains where it's easier to say whether something is correct or not. For example, in the case of cyber, like you mentioned that before, that cyber has been improving a lot, cyber capabilities as our models. And this is because in cyber, it's extremely easy to say. Are you correct? Did the cyber issue that you find is a real issue or not? It's very easy to test it. So there are domains where reinforcement learning is just easier to apply. But there's nothing, I would say, in the capacity of the model that is constraining the model to be as good at legal and medical and other domains.

1:00:08So the short answer is we know less about these domains. and definitely there are some domains that are easier to optimize for in reinforcement. Great. Let's talk about evals for a minute. That's a hugely important topic. Maybe to start, why is it so hard to evaluate a model in the first place? Evaluation has been harder and harder as models become better. And that's because the tasks that we ask to the model become more and more general and more and more open-ended. So now I maybe just say, build me a website that does X. Well, before in the past, I would just be like, hey, is there a specific bug in this implementation that you have?

1:01:00And it's much easier to say whether it is a bug because I can extract, I can have a human that says, here are all the bugs that you have, and then you can apply that automatically. while the website one is very hard to know what is the optimal answer because there are many good answers. There are many good ways of building a certain website. This open-ended nature of models really makes evals harder. There's also another issue is that models in specific axes are becoming better than the majority of humans. And so we have fewer and fewer humans that can actually evaluate these models in particular axes.

1:01:37so that's definitely constrained another one to be honest is kind of cultural most people want to improve the model and they they think that the best way to do that is kind of training the model when in reality finding issues and like making sure that we can quantify improvements is just as important if not more important but there's always this like cultural gap that was especially true I would say in the academic world up to like two years ago when evals were always fixed, benchmarks were always fixed, and even data sets were kind of always fixed, maybe let's say four years ago. And there was like a mentality shift of like, okay, data is actually critical.

1:02:18And now there's a lot of people working on data. And I think evals were still not quite there. People don't really fully, everyone knows that it's important, but like people don't really understand like how impactful it could be to work on evals. So actually my first product that opened AI just came in and I was like, I want to work on data and evals because I know that this is the thing that no one is working on. And as a result, I know that's super impactful to work on that. And yeah, the tide is shifting, but not fast enough. And is the pace of progress in model as a judge and AI, evaluating AI, is that moving as fast?

1:02:53Is that a distinct part of research? Or is that fundamentally the same idea or the same techniques? It's really fundamentally the same method. So there's like nothing. Also, most of the things that we do in evals, especially now that we have reinforcement learning, could just be applied nearly exactly as is during training. So that's another reason actually why evals are so complicated is that every time you build an eval, you actually build a way to build training datasets. So now you're going to optimize that training dataset. Well, even if it's not that eval, it's going to be the same type of data.

1:03:27And now you're going to do super well because we have this generalization of capabilities that I was telling you about, you will learn that on that other data set and now you'll become really good at that eval and that eval will become obsolete really quickly. So that's also an issue with evals. But yeah, to come back to your question, the model as a judge, it's really important. And I think it's one probably of the most important things because as we get better models, we have this self-reinforcing loop and we have this capability flywheel where better models become better teachers for other models.

1:04:05And this is really important for training, but then you can also do the same thing for evaluation. So a lot of my team works on that. And I think it's really critical is to work on this model as a judge kind of framework. Okay, fantastic. All right, so as we get towards the end of this conversation, I'd love to zoom out a bit and get your sense for where things might be heading. Obviously, it's incredibly hard to make predictions on AI years out, but let's call it the next 12, 18, maybe 24 months. Is your sense that things are going to continue progressing or are we heading towards something that could feel more like a discontinuity?

1:04:49In terms of progress, as I was saying before, I think it's always continuous. Now, the feeling of discontinuity will happen. It did happen three months ago with coding or four months ago with coding. And I think that will happen now in every other domains. Like most people are not feeling the same way, like kind of the capability of our model and the usefulness of our models, the same way as like coding and like software engineering is feeling right now. So this will definitely permeate, I think, through many other verticals. Now in terms of like capability bump in terms of, let's say, the verticals that we're already looking at, I think it will be more continuous.

1:05:28And there will never be big discontinuities. Most of them are always local discontinuities, but you zoom out and it always just feels pretty smooth. It's not always like this, but that has been the case most of the time. And I can definitely not predict when is the next big discontinuity. What is your sentiment on this general concept of accelerating loops in AI? So whether that's continual learning to make models more current and able to learn faster to this broader concept of AI building AI, like in an increasingly automated way, fact versus fiction. And what are you excited about? I'm extremely excited about continual learning.

1:06:11I think we haven't quite cracked it. I mean, we have like codex memories and that is helpful, but it's definitely not like the end state. I have a friend who always like tells me about again another type of plot that we should be looking at which is x-axis time, y-axis utility that you provide to users and right now or like usefulness basically of the models and right now actually most models at day zero if you just drop them in a company arguably they are more useful than most new employees so they start higher at T0. But then across time, they are mostly constant because they don't really learn kind of company knowledge.

1:06:57They don't really learn to be more efficient over time on doing the things that they are doing while humans learn really quickly. And what is important is kind of this integral or like kind of the area under the curve of these curves. And as a result, I think humans are still more useful in many cases. And that's why what we will need is to make like continual learning is to make this curve now monotonically increasing over time and basically make models more and more useful the longer they work in a certain environment. So I'm extremely excited about it. I'm actually surprised that we're not quite there yet.

1:07:37Three years ago when ChatGPT came out, I remember I was doing a startup with friends and we were thinking about working on continual learning and like personalization and like memories in general. and we're like, ah, OpenAI is going to do that in the next six months. They have all the data, they're going to figure it out and they have all the users and their models are going to learn super quickly from users. And three years later, I don't think we're there yet. And quickly in layman's terms, what is the fundamental difficulty? It's a good question. I actually don't quite know, to be completely honest with you.

1:08:10I don't quite know why it's taking us that long to figure it out. it's this type of domain that I think if we really put enough resources behind it we would figure it out of course especially when we talk about this memory inside of a company there's big questions about permissions and there's a lot of questions about privacy and what you can share and what you cannot across users but for a single user even for a single user we're not quite there And I don't quite know why, at least at the high level that I can talk about. I don't know why. Yeah. What you bring up is, I think, really interesting for AI builders and investors and startups, which is this question of the models getting increasingly smarter within an enterprise.

1:09:08In particular, there's like this whole tension between what the models are able to do and then what a lot of people have built around the model. So, you know, a year or two ago, it was RAG. These days, it's all about harnesses for agents. And a lot of people are wondering whether the models are going to end up eating the harness, whether the harness is just a temporary thing. From your perspective, what do you think happens? Yeah. I think harnesses can really improve the capability of a model right now. I think given that we're seeing this really fast progress in terms of capability, I personally wouldn't push that much on the harness.

1:09:51that unless it's like the harness is something for like very concrete goal that you're trying to achieve right now. So certain companies, like if they are focused on like a specific vertical, they want to go from this like 80 % maybe reliability to maybe the like 85%. And like Harnesses will give them that. And I think that's like very important, but like they will, they need to do it while knowing that they will have to retune that harness in the future. And I think that's totally fine. If you try to have like a general harness that will sustain over time, I don't think that will work. Harnesses for specific domains as a short-term thing that you need to do, I think there will always be so much you can do in harnesses.

1:10:42And if anything, I think everyone should do more of that. if they have a specific problem in mind, because we're leaving so much on the table without a good harness. Arguably, if we just, I think if we froze the models that we have right now and you really worked on the harness and like maybe like we also spend more time like training with like a great harness, I think people would really feel the AGI in every single domain or could already feel that in every single domain. But given that we're not freezing it and we're going to continue training better and better models. I think the harness, we don't really understand what the final harness will be.

1:11:21And it's not, and like it will always change. Some question about applications. So we alluded to your progress in different verticals. And that was, you know, GDB Val in general, but also how to bench telecom, which does complex customer service workflows and then progress against finance agents, automating 88.5 % of internal investment banking modeling tasks and then 51.1 % on Office QA Pro. So bit by bit, you're doing more and more of this. So do you think people should be building applications anymore or is ultimately, as we get closer to AGI, all of this going to be part of the model capabilities?

1:12:09which is there's so much space on pushing, pushing for like external companies or like startups pushing on specific verticals. I think there's so much space for that. The reason why is because a lot of people kind of think about intelligence and quotations and all like kind of like raw capability as being the real bar neck, but I don't think that's true. I think most of the time the bar neck is the last mile. it's like making sure that the model has access to has the right permissions or has also access to the right connectors and things like this and we are going to be very focused on this general aspect and I think there are other companies that should be focused on more of the verticals and providing maximum value of what we currently have.

1:12:59So I think there will always be a lot of space left for this last mile in different verticals. And I would highly encourage people to continue working on that. And maybe one day when we stop making horizontal progress, which I don't think is anytime soon, maybe we will start focusing on that. But yeah, that's not what we're doing now. Okay, well, that feels like a very optimistic note, at least for the startup ecosystem to end up on. Thank you so much, Jan. This was terrific. Really enjoyed it. Thank you so much for spending time with us. Great. Thanks, Matt. Hi, it's Matt Turk again. Thanks for listening to this episode of the Matt Podcast.

1:13:40If you enjoyed it, we'd be very grateful if you would consider subscribing if you haven't already or leaving a positive review or comment on whichever platform you're watching this or listening to this episode from. This really helps us build a podcast and get great guests. Thanks and see you on the next episode.