Michael Truell
speaker
105 appearances
2 recordings
2 series
first heard Oct 2024
last heard 14 Nov
Michael Truell’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 1 in all, peaking in Nov 2025 with 1.
Appearances
Yeah. Maybe an argument against formal verification is all you need.
Yeah. And I think that it's also important to note that this is having good bug finding models feels necessary to get to the highest reaches of having AI do more and more programming for you, where you're going to, you know, if the AI is building more and more of the system for you, you need to not just generate, but also verify.
And without that, some of the problems that we've talked about before with programming with these models will just become untenable. So it's not just for humans, like you write a bug, I write a bug, find the bug for me, but it's also being able to verify the AI's code and check it is really important.
You can also do a bunch of work, not even at the model level, of taking the biggest models and then maybe giving them access to a lot of information that's not just the code. it's kind of a hard problem to stare at a file and be like, where's the bug? And that's hard for humans often, right? And so often you have to run the code and being able to see things like traces and step through a debugger.
There's a whole other direction where it kind of tends toward that. And it could also be that there are kind of two different product form factors here. It could be that you have a really specialty model that's quite fast that's kind of running in the background and trying to spot bugs.
And it might be that sometimes, sort of to Arvid's earlier example about some nefarious input box bug, it might be that sometimes you want to like You know there's a bug. You're not just checking hypothesis-free. You're like, this is a problem. I really want to solve it.
And you zap that with tons and tons and tons of compute, and you're willing to put in $50 to solve that bug or something even more.
There is also a potential world where there's a technical solution to this like honor system problem too, where if we can get to a place where we understand the output of the system more, I mean, to the stuff we were talking about with like, you know, error checking with the LSP and then also running the code.
But if you could get to a place where you could actually somehow verify, oh, I have fixed the bug, maybe then the bounty system doesn't need to rely on the honor system too.
Yeah, I think that it has been an interesting journey adding each extra zero to the request per second. You run into all of these with the general components you're using for caching and databases run into issues as you make things bigger and bigger. And now we're at the scale where we get int overflows on our tables and things like that.
And then also, there have been some custom systems that we've built, like, for instance, our retrieval system for computing a semantic index of your codebase and answering questions about a codebase that have continually, I feel like, been one of the trickier things to scale.
It's tricky. I think we can do a lot better at computing the context automatically in the future. One thing that's important to note is there are trade-offs with including automatic context.
So the more context you include for these models, first of all, the slower they are and the more expensive those requests are, which means you can then do less model calls and do less fancy stuff in the background. Also, for a lot of these models, they get confused if you have a lot of information in the prompt.
So the bar for accuracy and for relevance of the context you include should be quite high. But already we do some automatic context in some places within the product. It's definitely something we want to get a lot better at. And I think that there are a lot of cool ideas to try there, both on the learning better retrieval systems, like better embedding models, better re-rankers.
I think that there are also cool academic ideas, stuff we've tried out internally, but also the field is grappling with writ large, about can you get language models to a place where you can actually just have the model itself, like understand a new corpus of information, And the most popular talked about version of this is, can you make the context windows infinite?
Then if you make the context windows infinite, can you make the model actually pay attention to the infinite context? And then after you can make it pay attention to the infinite context, to make it somewhat feasible to actually do it, can you then do caching for that infinite context? You don't have to recompute that all the time.
But there are other cool ideas that are being tried that are a little bit more analogous to fine-tuning of actually learning this information and the weights of the model. And it might be that you actually get sort of a qualitatively different type of understanding if you do it more at the weight level than if you do it at the in-context learning level.
I think the jury is still a little bit out on how this is all going to work in the end. But in the interim, us as a company, we are really excited about better retrieval systems and picking the parts of the code base that are most relevant to what you're doing. We could do that a lot better.
But anyway, what do you think about hiding the chain of thought? One consideration for open AI, and this is completely speculative, could be that they want to make it hard for people to distill these capabilities out of their model. it might actually be easier if you had access to that hidden chain of thought to replicate the technology.
Because that's pretty important data, like seeing the steps that the model took to get to the final result. So you could probably train on that also.
Showing 61–80 of 105 · page 4 of 6
← Previous
Next →