This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Tags
LW
Login
AI
•
Applied to
[Replication] Conjecture's Sparse Coding in Small Transformers
by
TagWrong
1m
ago
•
Applied to
Scaffolded LLMs: Less Obvious Concerns
by
Ruby
16m
ago
•
Applied to
[Linkpost] Faith and Fate: Limits of Transformers on Compositionality
by
Ruby
27m
ago
•
Applied to
LLMs Sometimes Generate Purely Negatively-Reinforced Text
by
TagWrong
2h
ago
•
Applied to
Palantir's AI models
by
TagWrong
2h
ago
•
Applied to
Conjecture: A standing offer for public debates on AI
by
TagWrong
4h
ago
•
Applied to
Explaining "Taking features out of superposition with sparse autoencoders"
by
TagWrong
4h
ago
•
Applied to
How not to write the Cookbook of Doom?
by
TagWrong
4h
ago
•
Applied to
[Linkpost] Mapping Brains with Language Models: A Survey
by
TagWrong
8h
ago
•
Applied to
Rational Animations is looking for an AI Safety scriptwriter, a lead community manager, and other roles.
by
TagWrong
8h
ago
•
Applied to
Distilling Singular Learning Theory
by
Liam Carroll
11h
ago
•
Applied to
Does anyone's full-time job include reading and understanding all the most-promising formal AI alignment work?
by
TagWrong
16h
ago
•
Applied to
Motivation in AI
by
nickasaf
17h
ago
•
Applied to
human intelligence may be alignment-limited
by
TagWrong
20h
ago
•
Applied to
AXRP Episode 22 - Shard Theory with Quintin Pope
by
TagWrong
1d
ago
•
Applied to
[Linkpost] World first as UK hosts inaugural AUKUS AI and autonomy trial
by
TagWrong
1d
ago
•
Applied to
Philosophical Cyborg (Part 2)...or, The Good Successor
by
TagWrong
1d
ago
•
Applied to
AI #16: AI in the UK
by
TagWrong
1d
ago
•
Applied to
A more effective Elevator Pitch for AI risk
by
Iknownothing
1d
ago