This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Tags
LW
Login
AI
•
Applied to
Does reducing the amount of RL for a given capability level make AI safer?
by
TagWrong
8h
ago
•
Applied to
OHGOOD: A coordination body for compute governance
by
Adam Jones
2d
ago
•
Applied to
CCS on compound sentences
by
Artyom Karpov
2d
ago
•
Applied to
"AI Safety for Fleshy Humans" an AI Safety explainer by Nicky Case
by
TagWrong
2d
ago
•
Applied to
Now THIS is forecasting: understanding Epoch’s Direct Approach
by
Elliot_Mckernon
2d
ago
•
Applied to
AI Clarity: An Initial Research Agenda
by
TagWrong
2d
ago
•
Applied to
LLM+Planners hybridisation for friendly AGI
by
TagWrong
3d
ago
•
Applied to
Mechanistic Interpretability Workshop Happening at ICML 2024!
by
TagWrong
3d
ago
•
Applied to
Weekly newsletter for AI safety events and training programs
by
Bryce Robertson
3d
ago
•
Applied to
CCS: Counterfactual Civilization Simulation
by
Pi Rogers
3d
ago
•
Applied to
Why I'm not doing PauseAI
by
TagWrong
3d
ago
•
Applied to
Key takeaways from our EA and alignment research surveys
by
Cameron Berg
3d
ago
•
Applied to
AI #61: Meta Trouble
by
TagWrong
3d
ago
•
Applied to
Ai Salon: Trustworthy AI Futures #1
by
TagWrong
3d
ago
•
Applied to
AI #62: Too Soon to Tell
by
TagWrong
3d
ago
•
Applied to
Q&A on Proposed SB 1047
by
TagWrong
3d
ago
•
Applied to
Please stop publishing ideas/insights/research about AI
by
Tamsin Leake
3d
ago