‹ BackHN Continuity

Thread

Jeeves. Reasoning improves Jev-like decision models

242 points · 95 comments · nicowaltz

  1. woadwarrior01 · · focus · HN ↗
    This isn't really surprising. LLM reasoning and before that, chain of thought prompting are essentially forms of test-time compute scaling.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.