Aarush Sah (@aarushsah_) 's Twitter Profile
Aarush Sah

@aarushsah_

Head of Evals @GroqInc | prev. @NousResearch

ID: 1566835226654822401

linkhttps://aarushsah.com calendar_today05-09-2022 17:07:01

1,1K Tweet

2,2K Followers

397 Following

Aarush Sah (@aarushsah_) 's Twitter Profile Photo

I’m hiring an Evals Engineer to join us at Groq Inc! You’ll own foundational eval infrastructure, launch impactful open-source tooling, and shape how we ship new models. Your opportunity for scope and autonomy will be large - perfect for someone driven, eager to apply what they

Ben Klieger (@benklieger) 's Twitter Profile Photo

Great research to check out, innovative approach to creating verifiers for hard to verify tasks. This has been the industry’s holy grail ever since RL improved easy to verify tasks like coding and math but seemingly left others with harder verification like writing behind.

Aarush Sah (@aarushsah_) 's Twitter Profile Photo

One year at Groq Inc today - it's passed by in the blink of an eye. Easily one of the most fun, challenging, and rewarding years of my life. So grateful to Gavin, sunny madra, Jonathan Ross, Omar Kilani, kraken, and the entire Groq team for creating an environment

One year at <a href="/GroqInc/">Groq Inc</a> today - it's passed by in the blink of an eye. Easily one of the most fun, challenging, and rewarding years of my life.

So grateful to <a href="/GavinSherry/">Gavin</a>, <a href="/sundeep/">sunny madra</a>, <a href="/JonathanRoss321/">Jonathan Ross</a>, <a href="/omarkilani/">Omar Kilani</a>, <a href="/kraken_9076/">kraken</a>, and the entire Groq team for creating an environment
Aarush Sah (@aarushsah_) 's Twitter Profile Photo

If any of the great folks at Windsurf are job hunting, I’d love to talk. We’re looking for someone with deep experience working on evals, post-training and/or synthetic data generation to join the evals team at Groq Inc. We move fast and care deeply about our work - if you

Aarush Sah (@aarushsah_) 's Twitter Profile Photo

I’d pay good money for an AI sentinel that I can ask to watch for an email, and will send me a text if it flags a match. Has anybody built this? Good hackathon project if not, cc Lucas Vogel krish

kelly (@kellyhongsn) 's Twitter Profile Photo

excited to share my latest technical report Chroma! we evaluated 18 LLMs, including state-of-the-art models, and observed model performance degradation with increasing input length