Viewing profile — pavpanchekha

A lot of algorithmic improvement in AI is ultimately bottlenecked by compute. It is very easy to come up with ideas that could improve models! But to prove that they do, especially…

Making Luna, which was already very cheap and extremely capable, 5x cheaper is crazy. I use Sol at work but Luna at home, and while there's definitely a difference, it doesn't feel…

For compiler work I found that Sol is noticably better than 5.5 (and I generally use OAI models because I like the Codex app), but Fable was still obviously better.

OpenAI used to make Codex-specific models, but they stopped. What I've gathered from interviews and similar is that training two models isn't worth the (small) lift from having a c…

University of Washington Programming Languages and Software Engineering (research group). I'm not at UW any more, I'm now at Utah, but some of the Herbie team is at UW and they pro…

Documented here but yes it's an average, of something similar to but not exactly the same as relative error: https://herbie.uwplse.org/doc/latest/error.html It's true that averages…

Author here. The speed up is modeled throughput, though the model is relatively naive. It's possible to disable branches by turning off the regimes flag, see https://herbie.uwplse.…

Author here. I've got a few papers about this problem (including one in submission), but it is very very hard to do, especially with acceptable overhead. The state of the art is ma…

It is, there's a page in the documentation about how errors are defined. Let me also add: Herbie generally gives the most accurate option it found first, and then the other stuff m…

Author here! Yes, the float distribution isn't what you want in practice, but distribution selector isn't really the right thing either, because a low probability bad result can st…

It was me. Damn it you're right! Will fix!

In calculus the core issue is that the concept of a "function" was undefined but generally understood to be something like what we'd call today an "expression" in a programming lan…

They're cheap but not free, especially at the front end of the CPU where it's just a lot more instructions to churn through. What the branch predictor gets you is it turns branches…

Horner's form is typically also more accurate, or at least, it is not bit-identical, so the compiler won't do it unless you pass -funsafe-math, and maybe not even then.

Deterministic output is incompatible with batching, which in turn is critical to high utilization on GPUs, which in turn is necessary to keep costs low.

Frontier models are now much bigger than an individual query, hence batching, MoE, etc. So this idea, while very plausible, has economic constraints, you'd need vast amounts of mem…

That pretty much is how CSS works! At the most basic level, Flow level is about widths down, heights up. But this basic model doesn't let you do a lot of things some people want to…

Author here—it is from Tufte CSS. I have a blog post [1] about how floats work. It is a nice example of there being unintuitive and also more-intuitive ways to achieve things in CS…

Author here. You're right that a lot of CSS's edge cases and implicit rules stem from other choices and implicit rules that maybe need to be reconsidered. But take this logic a ste…

Author here. I suppose it depends on what "rely on" means, but... have you ever used CSS to center text? Did you think much at all about what happens if the zoom level is high enou…

Author here. This specific quirk of CSS is minor, and probably if CSS didn't have this quirk it'd be fine. But I'd guess that you've at least once in your life been on your phone a…

Fixed

Author here. The problem isn't the technical challenge of writing a constraint solver. It's making sure that the resulting layout looks good, despite contradictory guidance from th…