task · first seen 18 Oct 2026
scalable oversight
Methods for humans to reliably supervise AI systems that may exceed human capabilities.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Towards Human-AI Complementarity for AI SafetyPapers · 18 Oct 2026 · Sander Lanbo Shi, Miranda Anna Christ, Eric Modesitt, Andrew Louis, Konrad Cheng…
- Humans Correct Their Judgments Through Debate, but Weaker AI Models Do NotPapers · 20 Oct 2026 · Maria Victoria Carro, Denise Alejandra Mester, Facundo Nieto, Oscar Agustin Stan…
- Rational Alignments of Superintelligences via DebatesPapers · 12 Nov 2026 · Thanawat Sornwanee
Latest sources
- Rational Alignments of Superintelligences via DebatesPapers · 12 Nov 2026 · Thanawat Sornwanee
- Humans Correct Their Judgments Through Debate, but Weaker AI Models Do NotPapers · 20 Oct 2026 · Maria Victoria Carro, Denise Alejandra Mester, Facundo Nieto, Oscar Agustin Stan…
- Towards Human-AI Complementarity for AI SafetyPapers · 18 Oct 2026 · Sander Lanbo Shi, Miranda Anna Christ, Eric Modesitt, Andrew Louis, Konrad Cheng…