evals

1 statements across 1 episodes · 0 bullish · 1 bearish · 1 people on the record · first statement Mar 8, 2025 by Chamath Palihapitiya · across every show →

Everything said about evals, oldest first

Mar 8, 2025 negative

Assertion Not checkable as stated

Chamath: AI labs are overfitting models on benchmarks, making scores unreliable

“And the problem, the dirty little secret of these model makers is that these guys are so trained on the evals that they're overfitting. And all this overfitting basically makes it pretty unreliable.”

Chamath Palihapitiya Mar 8, 2025 ▶ 1:27:47 Tariffs, Trump's Economic Endgame, Market Chaos, Bitcoin Reserve, CoreWeave IPO

Turn any episode into a week of clips.

This entire site, over 460 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.

evals

Everything said about evals, oldest first

Turn any episode into a week of clips.