Viewing profile — kcorbitt

And lately, the sweet spot has been moving upwards every 6-8 weeks with the model release cycle.

Is it?

Dang, hadn't seen that. Namespace collision strikes again.

I really like RLPR for when you have a known-good answer to compare to as well!

No, we don't do anything. Theoretically we could judge several times with different ordering. We could measure order bias really easily though; we just need to look at the average …

Thank! If there are any topics that you'd find particularly interesting, let me know and I can try to find time. :)

Hey HN, Kyle here, one of the co-founders of OpenPipe. Reinforcement learning is one of the best techniques for making agents more reliable, and has been widely adopted by frontier…

Looks cool! With vLLM v1, prefix caching is enabled by default and seems quite performant. Is the advantage of LMCache the fact that you can offload to CPU and disk as well? How mu…

I was curious about this so I had o3 do a bit of research. Turns out 300 L40s have more compute than any supercomputer before 2013 (and arguably before 2016, depending on how you c…

The real answer is that nobody trusts their automated evals enough to be confident that any given automatically-trained release actually improves performance, even if eval scores g…

It seems like the speedups here are most useful for small models, since on larger models a smaller fraction of the total time would be spent swapping between kernels? Would be inte…

There are many industries where you need lots of experience before you're a net contributor to productivity. This is true for everything from hairdressers to doctors. We have ways …

I wonder if they've trained the model to operate with a shallower stack; eg. the full model may be composed of 24 transformer blocks, but they've also trained it to accept embeddin…

It's very unlikely that they're doing their own pre-training, which is the longest and most expensive part of creating a frontier model (if they were, they'd likely brag about it).…

For "that last 10% of reliability" RL is actually working pretty well right now too! https://openpipe.ai/blog/art-e-mail-agent

Ok good questions here. By fine-tuning in this context I assume you mean "supervised fine-tuning", or SFT. SFT trains a model to produce a specific string of output tokens, given a…

Figured now was a good time to post this since we recently got surprisingly good results on training an email research agent. Link is above, but will put it here as well since I th…

Hey HN, I wanted to share a new project we've been working on for the last couple of months called ART ( https://github.com/OpenPipe/ART ). ART is a new open-source framework for t…

[dead]

We may be in a simulation, but your odds of being alive to see this (conditioned on being born as a human at some point) aren't that low. Around 7% of all humans ever born are aliv…

Yep. And tbh you probably don't even have to do this; the R1 paper found that just running SFT the base model with a relatively small number of monolingual reasoning traces was eno…