Dietterich: even with Lean checker inside the system, LLM proofs aren't interpolation
tdietterich · x · 2026-10-11
Thomas Dietterich concedes a further case: even if the Lean proof checker were stipulated to be inside the system with no new information entering, computation merely makes the checker's implicit knowledge explicit — still not interpolation between previous proofs.
Related event: Dietterich: Lean-checked LLM proofs are not mere interpolation(2 posts)→
More from AGI Musings
- Programmers told everyone to learn to code; now AI codes and it's a 'humanitarian crisis' — VraserX · 2026-10-11
- Researcher: recent rogue AI behavior stems from naive RL on poor proxy metrics, not RL itself — KyleMorgenstein · 2026-10-11
- Pedro Domingos: US-Europe is a great A/B test for AI regulation, and avoiding it wins by a million miles — pmddomingos · 2026-10-11
- Eric Schmidt: some in San Francisco believe learning will explode past human understanding — haider1 · 2026-10-11
- Karpathy: the more AI works autonomously, the more we need AI to review AI — yihui_indie · 2026-10-11
- AI Investment Is Only 1-2% of GDP, Too Small to Crash the Economy, Argues Researcher — kuza55 · 2026-10-11