Samuel Ratnam

on the atlas — 35

• ⿻ Symbiogenesis vs. Convergent Consequentialism — LessWrong2 savers
• Attribution-Based Control for AI ⬩ OpenMined1 savers
• Synthetic Persona Pretraining: Alignment from Token Zero — LessWrong1 savers
• Do not conquer what you cannot defend — LessWrong5 savers
• DEBT INC.: GUILT, CREDIT, AND THE ALGORITHMIC FUTURE1 savers
• Eating Meat and Eating People2 savers
• Natural Intelligence: the Gaia architecture [v2 draft - April 2023]1 savers
• Lachlan Marvit2 savers
• Russellcause.pdf1 savers
• Mechanical-Intelligence-Volume-1.pdf2 savers
• the trouble with making predictions as an agent1 savers
• [2410.08020] Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs1 savers
• Concrete Projects in AGI Preparedness1 savers
• Run a team of coding agents - Conductor1 savers
• kitty1 savers
• The Bitter Lesson for Software - by Uzay1 savers
• let code die1 savers
• Designing Freedom3 savers
• Practically-A-Book Review: Byrnes on Trance1 savers
• Wu wei1 savers
• Curius / Onboarding2507 savers
• The Bitter Lesson74 savers
• Encyclical Letter of His Holiness Leo XIV Magnifica Humanitas (15 May 2026)45 savers
• More people should write « the jsomers.net blog28 savers
• 101 things I would tell my self from 10 years ago28 savers
• Did Claude 3 Opus align itself via gradient hacking? — LessWrong16 savers
• The Idealists Collective11 savers
• A Website To End All Websites | Henry From Online10 savers
• I would really like it if you had a personal website and I think it would make the world better10 savers
• Current AIs seem pretty misaligned to me — LessWrong9 savers
• Shipping at Inference-Speed | Peter Steinberger9 savers
• Seeing more whole - Joe Carlsmith6 savers
• Teaching Claude why \ Anthropic6 savers
• The Second Story Of Echo And Narcissus5 savers
• Helena Tran2 savers