Simons Institute launches workshop on hallucinations to reliable autonomy
SharonYixuanLi · x · 2026-10-06
The Simons Institute kicked off its 'Trustworthy AI: From Hallucinations to Reliable Autonomy' workshop. Highlights include Charikar on language generation in the limit, Panigrahi on hallucination rates, Bareinboim on causal world models for agents, Sohl-Dickstein (Anthropic) on how misalignment scales, and Mengdi Wang on LabOS.
More from Research
- ICML area chair proposes desk-rejecting ~50% of papers amid AI-generated paper flood — maksym_andr · 2026-10-06
- Deemos publishes SIGGRAPH 2026 paper ACT: unified rigging, skinning and animation for 3D — sidahuj · 2026-10-06
- Cohere Labs at COLM: Chain-of-Thought Legibility Is Not Real Interpretability — Cohere_Labs · 2026-10-06
- NVIDIA Research Hiring Scientists, Interns for World Models and Diffusion LMs — ArashVahdat · 2026-10-06
- Gautam Kamath: math community's 'human understanding' push makes AI proofs worth revisiting — thegautamkamath · 2026-10-06
- Everyone uses AI for new math results; Kamath wants AI to simplify old proofs — thegautamkamath · 2026-10-06