This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Tags
LW
Login
AI
•
Applied to
To an LLM, everything looks like a logic puzzle
by
TagWrong
9h
ago
•
Applied to
AI Safety Institute's Inspect hello world example for AI evals
by
TheManxLoiner
10h
ago
•
Applied to
Ninety-five theses on AI
by
hamandcheese
13h
ago
•
Applied to
GPT-4o My and Google I/O Day
by
TagWrong
13h
ago
•
Applied to
AI #64: Feel the Mundane Utility
by
TagWrong
16h
ago
•
Applied to
AISN #35: Lobbying on AI Regulation Plus, New Models from OpenAI and Google, and Legal Regimes for Training on Copyrighted Data
by
aogara
17h
ago
•
Applied to
Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems
by
Gunnar_Zarncke
18h
ago
•
Applied to
A case for fairness-enforcing irrational behavior
by
TagWrong
22h
ago
•
Applied to
Podcast: Eye4AI on 2023 Survey
by
TagWrong
1d
ago
•
Applied to
Against "argument from overhang risk"
by
RobertM
1d
ago
•
Applied to
Introducing Statistical Utility Mechanics: A Framework for Utility Maximizers
by
kave
1d
ago
•
Applied to
"A Paradigm for AI Consciousness" - Seeds of Science call for reviewers
by
TagWrong
1d
ago
•
Applied to
Instruction-following AGI is easier and more likely than value aligned AGI
by
TagWrong
1d
ago
•
Applied to
How is GPT-4o Related to GPT-4?
by
TagWrong
2d
ago
•
Applied to
Tackling Moloch: How YouCongress Offers a Novel Coordination Mechanism
by
Hector Perez Arenas
2d
ago
•
Applied to
Teaching CS During Take-Off
by
habryka
2d
ago
•
Applied to
MIRI's May 2024 Newsletter
by
habryka
2d
ago
•
Applied to
Catastrophic Goodhart in RL with KL penalty
by
habryka
2d
ago