This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Tags
AF
Login
Apart Research
•
Applied to
Identifying semantic neurons, mechanistic circuits & interpretability web apps
by
Esben Kran
2mo
ago
•
Applied to
Automated Sandwiching & Quantifying Human-LLM Cooperation: ScaleOversight hackathon results
by
Esben Kran
3mo
ago
•
Applied to
We Found An Neuron in GPT-2
by
Joseph Miller
4mo
ago
•
Applied to
Generalizability & Hope for AI [MLAISU W03]
by
Esben Kran
5mo
ago
•
Applied to
Robustness & Evolution [MLAISU W02]
by
Esben Kran
5mo
ago
•
Applied to
AI improving AI [MLAISU W01!]
by
Esben Kran
5mo
ago
•
Applied to
Will Machines Ever Rule the World? MLAISU W50
by
Esben Kran
6mo
ago
•
Applied to
Join the AI Testing Hackathon this Friday
by
Esben Kran
6mo
ago
•
Applied to
ML Safety at NeurIPS & Paradigmatic AI Safety? MLAISU W49
by
Esben Kran
6mo
ago
•
Applied to
NeurIPS Safety & ChatGPT. MLAISU W48
by
Esben Kran
6mo
ago
•
Applied to
Results from the interpretability hackathon
by
Esben Kran
7mo
ago