Eric Huang

on the atlas — 58

• Statement on the US government directive to suspend access to Fable 5 and Mythos 5 \ Anthropic9 savers
• on-fairy-stories1.pdf1 savers
• Oxford_Movement1 savers
• [2602.04899] Phantom Transfer: Data-level Defences are Insufficient Against Data Poisoning3 savers
• Ad-Free Privacy Tool/Service Recommendations - Privacy Guides1 savers
• Encyclical Letter of His Holiness Leo XIV Magnifica Humanitas (15 May 2026)45 savers
• SLOW-SCIENCE.org — Bear with us, while we think.2 savers
• Eurasianism1 savers
• Phantom Transfer and the Basic Science of Data Poisoning — LessWrong1 savers
• DeepSeek_V4.pdf · deepseek-ai/DeepSeek-V4-Pro at main1 savers
• A Field Guide to AI Safety—Asterisk1 savers
• Shoggoth1 savers
• Curius / Onboarding2507 savers
• 2025 letter | Dan Wang62 savers
• AI 202749 savers
• What's going on here, with this human? - Graham Duncan Blog45 savers
• Dario Amodei — The Adolescence of Technology44 savers
• The First Fully General Computer Action Model | blog35 savers
• On the Biology of a Large Language Model31 savers
• The Grug Brained Developer28 savers
• The Persona Selection Model: Why AI Assistants might Behave like Humans28 savers
• The New World - Colossus24 savers
• Whole Earth Index22 savers
• ALIGNMENT - by vincent huang - a slice of my mind22 savers
• Circuit Tracing: Revealing Computational Graphs in Language Models18 savers
• Alignment is not solved but it increasingly looks solvable17 savers
• Did Claude 3 Opus align itself via gradient hacking? — LessWrong16 savers
• The Era of Experience Paper.pdf15 savers
• Alignment remains a hard, unsolved problem — LessWrong14 savers
• The Scaling Hypothesis · Gwern.net14 savers
• Claude Mythos Preview System Card14 savers
• The Second Half – Shunyu Yao – 姚顺雨13 savers
• Claude Mythos Preview \ red.anthropic.com13 savers
• Resonant Computing Manifesto13 savers
• DeepSeek-R112 savers
• They're Made out of Meat11 savers
• John Carmack on Idea Generation11 savers
• Maker's Schedule, Manager's Schedule10 savers
• i have found a way out - by Sophie Kim10 savers
• An OpenAI model has disproved a central conjecture in discrete geometry | OpenAI9 savers
• [AI Futures Model] Supplementary materials - Google Docs5 savers
• Natural-emergent-misalignment-from-reward-hacking-paper.pdf5 savers
• A small number of samples can poison LLMs of any size \ Anthropic5 savers
• Philosophy behind Claude's Constitution5 savers
• Guide world5 savers
• Qian Xuesen5 savers
• Searching for God in Silicon Valley - by Avital Balwit5 savers
• Existential_Risk_and_Growth.pdf4 savers
• [2604.16812] Introspection Adapters: Training LLMs to Report Their Learned Behaviors4 savers
• When To Do What You Love4 savers
• Can activation verbalizers surface an internal chain of thought? — LessWrong4 savers
• Attention-Residuals/Attention_Residuals.pdf at master · MoonshotAI/Attention-Residuals3 savers
• How funerals keep Africa poor - David Oks3 savers
• Reflections from Kunming, an unglobalized part of the world3 savers
• Burkean Longtermism2 savers
• Antikythera | Antikythera2 savers
• The Grugbrained CEO2 savers
• Carcinisation - Wikipedia2 savers