Geoffrey Irving puts >90% on unbounded-depth CSETH, unsure about finite depth
geoffreyirving · x · 2026-10-29
Geoffrey Irving says he considers unbounded-depth CSETH very likely true (probability >90%), but it remains unclear which way the bounded-depth version goes. He notes the funniest possible outcome would be if it were false for d ≤ 7 and true beyond that.
Related event: DeepMind's Irving Assigns High Probability to Unbounded-Depth CSETH(2 posts)→
More from Research
- Stanford's FACT: Force-Aware Robot Foundation Model Trained on 2,000h Human Data — yining_hong · 2026-10-29
- 86M-param decoder-only transformer plays chess on Lichess, full notebook public — andreisavu · 2026-10-29
- Harvard experiment finds AI reviews dominate human peer reviews — RexDouglass · 2026-10-29
- Box2D WASM upgraded to V3.2 with open-source PBMPM solver coupling code and demo — Birchlabs · 2026-10-29
- Unprompted conf: model internals are the new Windows internals, says Matt Suiche — moyix · 2026-10-29
- Family-aware All of Us benchmark for polygenic prediction and genomic ML released — anshulkundaje · 2026-10-29