This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Tags
AF
Login
AI
•
Applied to
How the AI safety technical landscape has changed in the last year, according to some practitioners
by
TagWrong
16h
ago
•
Applied to
A Visual Task that's Hard for GPT-4o, but Doable for Primary Schoolers
by
Ruben Bloom
17h
ago
•
Applied to
Unaligned AI is coming regardless.
by
verbalshadow
18h
ago
•
Applied to
New User's Guide to LessWrong
by
roboticali
1d
ago
•
Applied to
Pacing Outside the Box: RNNs Learn to Plan in Sokoban
by
TagWrong
2d
ago
•
Applied to
Does robustness improve with scale?
by
TagWrong
2d
ago
•
Applied to
Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs
by
Ruben Bloom
2d
ago
•
Applied to
"AI achieves silver-medal standard solving International Mathematical Olympiad problems"
by
TagWrong
2d
ago
•
Applied to
[Talk transcript] What “structure” is and why it matters
by
Alex_Altair
2d
ago
•
Applied to
AI #74: GPT-4o Mini Me and Llama 3
by
TagWrong
2d
ago
•
Applied to
AI Constitutions are a tool to reduce societal scale risk
by
TagWrong
2d
ago
•
Applied to
Determining the power of investors over Frontier AI Labs is strategically important to reduce x-risk
by
Lucie Philippon
2d
ago
•
Applied to
A framework for thinking about AI power-seeking
by
TagWrong
3d
ago
•
Applied to
Llama Llama-3-405B?
by
TagWrong
3d
ago
•
Applied to
AI Safety Memes Wiki
by
plex
3d
ago
•
Applied to
Research Discussion on PSCA with Claude Sonnet 3.5
by
Robert Kralisch
3d
ago
•
Applied to
You should go to ML conferences
by
Jan_Kulveit
3d
ago
•
Applied to
The last era of human mistakes
by
TagWrong
3d
ago