This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Tags
AF
Login
AI Safety Camp
•
Applied to
Invitation to lead a project at AI Safety Camp (Virtual Edition, 2025)
by
Linda Linsefors
15d
ago
•
Applied to
Some reasons to start a project to stop harmful AI
by
Remmelt Ellen
16d
ago
•
Applied to
Thinking About What Are Propensity Evaluations [WIP]
by
Maxime Riché
20d
ago
•
Applied to
A Taxonomy Of AI System Evaluations [WIP]
by
Maxime Riché
20d
ago
•
Applied to
Self-Other Overlap: A Neglected Approach to AI Alignment
by
Remmelt Ellen
26d
ago
•
Applied to
Whirlwind Tour of Chain of Thought Literature Relevant to Automating Alignment Research.
by
sevdeawesome
2mo
ago
•
Applied to
Immunization against harmful fine-tuning attacks
by
Domenic Rosati
3mo
ago
•
Applied to
Training-time domain authorization could be helpful for safety
by
Domenic Rosati
3mo
ago
•
Applied to
Launching applications for AI Safety Careers Course India 2024
by
Axiom_Futures
4mo
ago
•
Applied to
"Open Source AI" is a lie, but it doesn't have to be
by
jacobhaimes
4mo
ago
•
Applied to
AISC9 has ended and there will be an AISC10
by
Linda Linsefors
4mo
ago
•
Applied to
Towards a formalization of the agent structure problem
by
Alex_Altair
5mo
ago
•
Applied to
[Aspiration-based designs] 1. Informal introduction
by
Jobst Heitzig
5mo
ago
•
Applied to
Podcast interview series featuring Dr. Peter Park
by
jacobhaimes
5mo
ago
•
Applied to
INTERVIEW: Round 2 - StakeOut.AI w/ Dr. Peter Park
by
jacobhaimes
6mo
ago
•
Applied to
A Review of Weak to Strong Generalization [AI Safety Camp]
by
sevdeawesome
6mo
ago
•
Applied to
INTERVIEW: StakeOut.AI w/ Dr. Peter Park
by
jacobhaimes
6mo
ago
•
Applied to
Paper review: “The Unreasonable Effectiveness of Easy Training Data for Hard Tasks”
by
Vassil Tashev
6mo
ago
•
Applied to
Inducing human-like biases in moral reasoning LMs
by
artkpv
7mo
ago