Become a Member

Regulation TrackerLaws, orders and treaties read for their security duties and clocks Standards & FrameworksAttack taxonomies, control catalogues and frontier frameworks AI Incident DatabaseThe security incident record, with mechanism and lesson Research Paper LibraryThe papers that define the field, summarised OSS DirectoryRed teaming, guardrail, supply chain and evaluation tools Case StudiesProgrammes built, with measured outcomes AI Vulnerability TrackerCVEs and advisories for the components AI systems are built from

Latest in the tracker

New York Stop Addictive Feeds Exploitation (SAFE) for Kids Act and implementing rulesNew York's law restricting algorithmic feeds for minors takes effect on 25 January 2027 under final rules published in July 2026, with certified age assurance and $5,000-per-violation penalties.

Knowledge Base Regulation Tracker Standards & Frameworks OSS Directory AI Incident Database Research Paper Library Case Studies Society Articles News Jobs About Charter Become a Member

Home/Research Paper Library/AI safety via debate

AI safety via debate

Proposed debate as a scalable oversight mechanism, the origin of a research line now tested empirically with LLM debaters.

debatescalable oversightopenai

Research question

Can humans judge questions beyond their ability by watching AI debaters?

Key findings

Debate between two agents judged by a human can, in theory, align systems more capable than the judge - Toy experiments on MNIST show honest debaters have an advantage

Sources

arxiv.orghttps://arxiv.org/abs/1805.00899

Contribute

Spot an error, or know a record we should add? Members can propose additions and submit corrections.

Submit research Report a correction or request removal