open source evals

1 statements across 1 episodes · 0 bullish · 1 bearish · 1 people on the record · first statement Apr 15, 2025 by Michelle Pokrass · across every show →

Everything said about open source evals, oldest first

Apr 15, 2025 negative

Insight

Open-source AI benchmarks omit critical tasks because they are hard to grade

“And these are useful instructions, but we find that many of the really interesting instructions are actually challenging to grade. And so the open source evals often don't have them.”

Michelle Pokrass Apr 15, 2025 ▶ 18:56 GPT 4.1: The New OpenAI Workhorse

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

open source evals

Everything said about open source evals, oldest first

Turn any episode into a week of clips.