AI ALIGNMENT FORUM
Tags
AF

Debate (AI safety technique)

•

Applied to Embracing complexity when developing and evaluating AI responsibly by Aliya Amirova 2mo ago

•

Applied to Reinforcement Learning from Information Bazaar Feedback, and other uses of information markets by Abhimanyu Pallavi Sudhir 3mo ago

•

Applied to GPT-3.5 judges can supervise GPT-4o debaters in capability asymmetric debates by Charlie George 4mo ago

•

Applied to Inference-Only Debate Experiments Using Math Problems by Arjun Panickssery 5mo ago

•

Applied to Against AI As An Existential Risk by Noah Birnbaum 5mo ago

•

Applied to Debate, Oracles, and Obfuscated Arguments by sunwillrise 5mo ago

•

Applied to Control Vectors as Dispositional Traits by Gianluca Calcagni 6mo ago

•

Applied to NYU Debate Training Update: Methods, Baselines, Preliminary Results by samarnesen 6mo ago

•

Applied to On scalable oversight with weak LLMs judging strong LLMs by Zachary Kenton 6mo ago

•

Applied to AI Debate Stability: Addressing Self-Defeating Responses by Annie Szorkin 6mo ago

•

Applied to Alignment Gaps by kcyras 6mo ago

•

Applied to NYU Code Debates Update/Postmortem by David Rein 7mo ago

•

Applied to Debating with More Persuasive LLMs Leads to More Truthful Answers by Akbir Khan 10mo ago

•

Applied to OpenAI Credit Account (2510$) by Emirhan BULUT 1y ago

•

Applied to Anthropic Fall 2023 Debate Progress Update by Shay Ben Moshe 1y ago

•

Applied to Deception Chess: Game #2 by RobertM 1y ago