Jo J.

on the atlas — 70

• Mnemonic portraits for 19,023 human genes — LessWrong6 savers
• When does training a model change its goals?1 savers
• How training-gamers might function (and win)1 savers
• Auditing failures vs concentrated failures — AI Alignment Forum1 savers
• Notes on handling non-concentrated failures with AI control: high level methods and different regimes1 savers
• Why it's hard to make settings for high-stakes control research1 savers
• Catching AIs red-handed1 savers
• Lorem ipsum1 savers
• [1507.01986] Toward Idealized Decision Theory2 savers
• Top 10 Animal Charities to Donate to in 20261 savers
• The Most Important Charts In The World - by Zvi Mowshowitz1 savers
• Why Nothing Ever Happens • Chasing Sunsets2 savers
• How Occultists Remade the World | Compact1 savers
• llm assistant personas seem increasingly incoherent (some subjective observations) — LessWrong7 savers
• Andrea del Verrocchio1 savers
• Better Babblers - by Robin Hanson - Overcoming Bias1 savers
• The Multi-Armed Bandit Problem and Its Solutions | Lil'Log3 savers
• Reflective Equilibrium (Stanford Encyclopedia of Philosophy)3 savers
• Pause Your Feedback Loops1 savers
• Child’s Play, by Sam Kriss75 savers
• Learning By Writing37 savers
• The Persona Selection Model: Why AI Assistants might Behave like Humans28 savers
• https://cs.stanford.edu/~jsteinhardt/ResearchasaStochasticDecisionProcess.html26 savers
• Please don't throw your mind away — LessWrong24 savers
• Training the Idea Muscle | Alexandria23 savers
• Why Tool AIs Want to Be Agent AIs · Gwern.net18 savers
• Circuit Tracing: Revealing Computational Graphs in Language Models18 savers
• Dario Amodei — The Urgency of Interpretability17 savers
• Introducing talkie: a 13B vintage language model from 193017 savers
• Did Claude 3 Opus align itself via gradient hacking? — LessWrong16 savers
• Automated Weak-to-Strong Researcher15 savers
• Alignment remains a hard, unsolved problem — LessWrong14 savers
• The high-return activity of raising others' aspirations - Marginal REVOLUTION14 savers
• The Smol Training Playbook: The Secrets to Building World-Class LLMs - a Hugging Face Space by HuggingFaceTB13 savers
• They're Made out of Meat11 savers
• New York’s Best (Fake) Steak House Opens Up - The New York Times11 savers
• The behavioral selection model for predicting AI motivations — LessWrong10 savers
• Natural Language Autoencoders \ Anthropic9 savers
• Approximating KL Divergence9 savers
• The case for ensuring that powerful AIs are controlled — LessWrong9 savers
• Eliezer's Unteachable Methods of Sanity — LessWrong9 savers
• Reward Hacking in Reinforcement Learning | Lil'Log9 savers
• Highly Opinionated Advice on How to Write ML Papers — AI Alignment Forum8 savers
• My picture of the present in AI — LessWrong8 savers
• Off Target | CNAS7 savers
• davidbau.com In Defense of Curiosity7 savers
• Building up to an Internal Family Systems model — LessWrong6 savers
• AI safety undervalues founders — LessWrong6 savers
• Borges-Tlön-Uqbar-Orbius-Tertius.pdf6 savers
• Reward is not the optimization target — LessWrong6 savers
• Bitter Lessons from Distillation Robustifies Unlearning4 savers
• We spent 2 hours working in the future - METR4 savers
• Hackers and Painters4 savers
• The Case Against AI Control Research — LessWrong4 savers
• Learn like an athlete, knowledge workers should train - Marginal REVOLUTION4 savers
• When RAND Made Magic in Santa Monica—Asterisk4 savers
• Don’t Outsource Your Thinking4 savers
• Against neutrality about creating happy lives - Joe Carlsmith4 savers
• Why I'm not a philosopher4 savers
• The Gentle Romance - by Richard Ngo - Asimov Press4 savers
• On The Independence Axiom — LessWrong3 savers
• My journey to the microwave alternate timeline — LessWrong3 savers
• Book Review: Design Principles of Biological Circuits - LessWrong3 savers
• The Electric Typewriter3 savers
• [2402.14740] Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs2 savers
• [2509.04259] RL's Razor: Why Online Reinforcement Learning Forgets Less2 savers
• Possibility and Could-ness — LessWrong2 savers
• AI catastrophes and rogue deployments - by Buck Shlegeris2 savers
• Anthropic's leading researchers acted as moderate accelerationists — LessWrong2 savers
• How to Make Yourself Into a Learning Machine - Superorganizers - Every2 savers