reasoning training tokens

1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Mar 31, 2025 by Kevin Scott · across every show →

Everything said about reasoning training tokens, oldest first

Mar 31, 2025 neutral
Insight
Scott: Reasoning models require different training tokens than fact recallers
“What you want models to be able to do is to be able to reason over information. So like if you give them access to information, like how well are they able to reason over a set of information to go do something that's useful for you? And so you just need diffe…”
Kevin Scott Mar 31, 2025 ▶ 12:40 Kevin Scott, CTO @ Microsoft: An Evaluation of Deepseek and How We Underestimate the Chinese · 20VC with Harry Stebbings
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 1,200 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.