curius graph

all pages

showing 36351-36400 of 160880 pages (sorted by popularity)
xkcd: Settling
How can we solve diffuse threats like research sabotage with AI control?
2406.05946
2306.09479
Generalization on the Unseen, Logic Reasoning and Degree Curriculum
Tasks – Inspect
Decision Theories: A Less Wrong Primer — LessWrong
Causal Decision Theory (Stanford Encyclopedia of Philosophy)
OpenAI now has an RL API which is broadly accessible — AI Alignment Forum
Multiverse-wide cooperation in a nutshell — EA Forum
Acausal Trade - LessWrong
Jones Foods - Quality Poultry Since 2021
Thoughts on the conservative assumptions in AI control
Understanding the Parameter Decomposition papers
OpenAI-RL-example/rl_test.py at master · rgreenblatt/OpenAI-RL-example
Recent Redwood Research project proposals
Notes on handling non-concentrated failures with AI control: high level methods and different regimes — LessWrong
How my views on AI changed every year 2017-2024 - Alexey Guzey
[2507.12856] Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)
2412.14093
Exploration hacking: can reasoning models subvert RL? — LessWrong
2310.09144
2210.10760
1906.01820
Claude, GPT, and Gemini All Struggle to Evade Monitors — LessWrong
1810.08575
Tanuki/tanuki.py: Prompt engineering for developers
AI for AI safety - Joe Carlsmith's Substack
0.999… = 1, with Rigour – BorisTheBrave.Com
Harry Potter and the Methods of Rationality, Chapter 6: The Planning Fallacy
Harry Potter and the Methods of Rationality, Chapter 8: Positive Bias
AI Auditing 2027 - by Miles Brundage - Miles’s Substack
Why I'm not afraid of superintelligent AI taking over the world
AGI Politics - by Jason Hausenloy - The First Scattering
Emotive conjugation - Wikipedia
Scientific Knowledge and Its Social Problems - Wikipedia
I Am Teaching Maths and It Is Personal | by Innocent Ingabire | Sep, 2025 | Medium
Threading the Needle | Anton Leicht | Substack
Don’t Build An AI Safety Movement - by Anton Leicht
The Bottom Line — LessWrong
You Can Face Reality — LessWrong
Untitled
Functions describe the world. - hayden so
Know the players of the game - hayden so
About | Atticus Wang
Minding our way to the heavens
Comments - Book Review: If Anyone Builds It, Everyone Dies
Vipassana Meditation
Paolo Borsellino - Wikipedia
Giovanni Falcone - Wikipedia