Speaker unverified: belief

Transcript context

…icient information gathering before trying to solve the task. And so if you provide all, if you provide instructions that it should do information [00:42:00] gathering beforehand, it tends to do well. If you don't provide sufficient instructions, it will try to solve the task without, like, fully understanding the task first, and then fail, and then you need to go back and give feedback. You know, additional feedback. Another example, like, I, I love this example. While I was developing the the monitor website that I, I showed here, we hit a really tricky bug where it was writing out a cache file to a different directory than it was reading the cache file from. And I had no idea what to do. I had no idea what was going on. I, I thought the bug was in a different part of the code, but what I asked it to do was come up with five possible reasons why this could be failing and decreasing order of likelihood and examine all of them. And that worked and it could just go in and like do that. So like I think a certain level of like scaffolding about like how it should sufficiently Gather all the information that's necessary in order to solve a task is like, if that's missing, then that's probably the biggest failure point at the moment. Yeah, self, self improving. So I think the biggest reason, like the simplest possible way to create a self improving agent. The problem with that is to have a really, really strong language model that with infinite context, and it can just go back and look at like all of its past experiences and, you know, learn from them. You might also want to remove the bad stuff just so it doesn't over index on it's like failed past experiences. But the problem is a really powerful language model is large. Infinite context is expensive. We don't have a good way to [00:44:00] index into it because like rag, Okay. At least in my experience, RAG from language to code doesn't work super well. So I think in the end, it's like, that's the way I would like to solve this problem. I'd like to have an infinite context and somehow be able to index into it appropriately. And I think that would mostly solve it. Another thing you can do is fine tuning. So I think like RAG is one way to get information into your model. Fine tuning is another way to get information into your model. So. That might be another way of continuously improving. Like you identify when you did a good job and then just add all of the good examples into your model. Yep. Yeah, I mean, we're calling them workflows, but they're simpler. Yeah, I totally, I think it's possible. It's just, you know, not, not trivial at the same time. I'll explain the two curves. So basically, the base, the baseline is just an agent that does it from scratch every time. And this curve up here is agent workflow memory where it's like adding the successful experiences back into the prompt. Why is this improving? The reason why is because just it failed on the first few examples and for the average to catch up it, it took a little bit of time. So it's not like this is actually improving it. You could just basically view the this one is constant and then this one is like improving. or the average to catch up it, it took a little bit of time. So it's not like this is actually improving it. You could just basically view the this one is constant and then this one is like improving. Like this, basically you can see it's continuing to go [00:46:00] up. When you say authentication, you mean like credentials, like, yeah. Yeah. Great questions. So. My preferred solution to this at the moment is GitHub like fine grained authentication tokens and GitHub fine grained authentication tokens allow you to specify like very free. On a very granular basis on this repo, you have permission to do this, on this repo, you have permission to do this. You also can prevent people from pushing to the main branch unless they get approved. You can do all of these other things. And I think these were all developed for human developers. Or like, the branch protection rules were developed for human developers. The fine grained authentication tokens were developed for GitHub apps. I think for GitHub, maybe [00:47:00] just pushing this like a little bit more is the way to do this. For other things, they're totally not prepared to give that sort of fine grained control. Like most APIs don't have something like a fine grained authentication token. And that goes into my like comment that we're going to need to prepare the world for agents, I think. But I think like the GitHub authentication tokens are like a good template for how you could start doing that maybe, but yeah, I don't, I don't, I don't have an answer. Okay. Yeah. I'm going to finish up. Let, let me just see. Okay. So this one this one did write a script. I'm not going to actually read it for you. And then the other one, let's see. Yeah. So it sent a PR, sorry. What is, what is the PR URL? So I don't, I don't know if this sorry, that's taking way longer than it should. Okay, cool. Yeah. So this one sent a PR. I'll, I'll tell you later if this actually like successfully Oh, no, it's deployed on Vercel, so I can actually show you, but let's, let me try this real quick. Sorry. I know I don't have time. Yeah, there you go. I have pie charts now. So it's so fun. It's so fun to play with these things. Cause you could just do that while I'm giving a, you know, talk and things like that. So, yeah, thanks.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.