Kevin Zhang

on the atlas — 19

• Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations — LessWrong2 savers
• The Death of the University Degree - by Carl Hendrick1 savers
• A Cascade of Conscientiousness - by Dean W. Ball1 savers
• Automating philosophy if Timothy Williamson is correct — LessWrong1 savers
• Claude is Now Alignment-Pretrained — LessWrong1 savers
• Red-teaming a network of agents: Understanding what breaks when AI agents interact at scale - Microsoft Research1 savers
• No Country for Young Men - by Terminally_Drifting1 savers
• Not a Paper: "Frontier Lab CEOs are Capable of In-Context Scheming" — LessWrong2 savers
• [2502.15657] Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?1 savers
• [2603.08640] PostTrainBench: Can LLM Agents Automate LLM Post-Training?1 savers
• The Bitter Lesson74 savers
• How to be More Agentic - by Cate Hall - Useful Fictions19 savers
• Automated Weak-to-Strong Researcher15 savers
• Becoming perceptive - by Henrik Karlsson12 savers
• A vision researcher’s guide to some RL stuff: PPO & GRPO - Yuge (Jimmy) Shi8 savers
• How we built our multi-agent research system \ Anthropic6 savers
• Everyone Can Tell if You're a Serious Person5 savers
• How to increase your surface area for luck - by Cate Hall4 savers
• How to walk through walls - by Henrik Karlsson3 savers