This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Tags
AF
Login
Debate (AI safety technique)
•
Applied to
Debating with More Persuasive LLMs Leads to More Truthful Answers
by
Akbir Khan
3mo
ago
•
Applied to
OpenAI Credit Account (2510$)
by
Emirhan BULUT
3mo
ago
•
Applied to
Anthropic Fall 2023 Debate Progress Update
by
Shay Ben Moshe
4mo
ago
•
Applied to
Deception Chess: Game #2
by
RobertM
5mo
ago
•
Applied to
AI debate: test yourself against chess 'AIs'
by
Richard Willis
5mo
ago
•
Applied to
Debate helps supervise human experts [Paper]
by
Roger Dearnaley
5mo
ago
•
Applied to
AI Safety 101 - Chapter 5.1 - Debate
by
Charbel-Raphael Segerie
6mo
ago
•
Applied to
Evaluating Superhuman Models with Consistency Checks
by
Daniel Paleka
9mo
ago
•
Applied to
A Proposal for AI Alignment: Using Directly Opposing Models
by
Arne B
1y
ago
•
Applied to
Empathy bandaid for immediate AI catastrophe
by
installgentoo
1y
ago
•
Applied to
[New LW Feature] "Debates"
by
Jim Babcock
1y
ago
•
Applied to
Why I’m not working on {debate, RRM, ELK, natural abstractions}
by
Steve Byrnes
1y
ago
•
Applied to
Alignment with argument-networks and assessment-predictions
by
Tor Økland Barstad
1y
ago