Dillon Nguyen

on the atlas — 86

• A global workspace in language models \ Anthropic20 savers
• FLI AI Safety Research Landscape - Extended - v0.431 savers
• Ten AI safety projects I'd like people to work on — LessWrong1 savers
• You Need A Theory of Victory - by Jason Hausenloy1 savers
• Strategic Taste5 savers
• Help Alex Bores Win! Why and How [shared] - Google Docs2 savers
• The most overlooked roles in AI safety | 80,000 Hours1 savers
• 3-2-1: On improving the world, feeling wealthy, and managing your three selves - James Clear1 savers
• Instrumental convergence — LessWrong1 savers
• The American Involution - otothebo1 savers
• The case for countermeasures to memetic spread of misaligned values — LessWrong1 savers
• Why I don't persuade people to do AI safety3 savers
• Find a way - by Cate Hall - Useful Fictions2 savers
• The Singularity is a Veil of Ignorance — EA Forum1 savers
• All my (vegan) fitness advice - Part 1: Exercise and etiquette — Andy Masley1 savers
• Opus 4.8 Part 2: Model Welfare - by Zvi Mowshowitz1 savers
• Contra Hoel On Aristocratic Tutoring - by Scott Alexander1 savers
• Art Gallery - by Roman's Attic - Roman’s Attic1 savers
• Defileo🔮 on X: "Claude + Obsidian have to be illegal" / X1 savers
• Looking for Alice - by Henrik Karlsson - Escaping Flatland84 savers
• Child’s Play, by Sam Kriss75 savers
• Productivity - Sam Altman52 savers
• sparkly people and how to find them - by Anson Yu52 savers
• What's going on here, with this human? - Graham Duncan Blog45 savers
• escaping flatland: career advice for CS undergrads41 savers
• Pain is not the unit of Effort38 savers
• Intentionally Making Close Friends — Neel Nanda38 savers
• The Persona Selection Model: Why AI Assistants might Behave like Humans28 savers
• How to win a best paper award (or, an opinionated take on how to do important research)24 savers
• Post 38: On Slack - Having room to be excited — Neel Nanda23 savers
• The machines are fine. I'm worried about us.22 savers
• How to be More Agentic - by Cate Hall - Useful Fictions19 savers
• Verbalizable Representations Form a Global Workspace in Language Models17 savers
• Did Claude 3 Opus align itself via gradient hacking? — LessWrong16 savers
• AGI Ruin: A List of Lethalities - LessWrong15 savers
• Top Performers are Pathologically Ambitious - by Matt Beard15 savers
• Greg - Sam Altman15 savers
• Why we stopped making Einsteins - by Erik Hoel13 savers
• 2028: Two scenarios for global AI leadership \ Anthropic12 savers
• A woefully incomplete guide to technical upskilling12 savers
• i think about it all the time - by Claire Wang10 savers
• i have found a way out - by Sophie Kim10 savers
• An OpenAI model has disproved a central conjecture in discrete geometry | OpenAI9 savers
• Clawed - by Dean W. Ball - Hyperdimensional9 savers
• The case for ensuring that powerful AIs are controlled — LessWrong9 savers
• Ask vs guess culture - by Jean Hsu - Tech and Tea9 savers
• Why we didn't get a malaria vaccine sooner - Works in Progress9 savers
• Highly Opinionated Advice on How to Write ML Papers — AI Alignment Forum8 savers
• MATS 9 Retrospective & Advice — LessWrong8 savers
• My picture of the present in AI — LessWrong8 savers
• What failure looks like - LessWrong8 savers
• - - Sam Altman7 savers
• The Eternal Sloptember | the singularity is nearer7 savers
• llm assistant personas seem increasingly incoherent (some subjective observations) — LessWrong7 savers
• There should be ‘general managers’ for more of the world’s important problems6 savers
• Think Tanks Have Defeated Democracy6 savers
• A Theory of Deep Learning | Elements of a Vector Space6 savers
• Plans A, B, C, and D for misalignment risk — LessWrong5 savers
• The Unintelligibility is Ours: Notes on Chain of Thought5 savers
• The Anatomy of Determination5 savers
• The Skill of Noticing Emotions - LessWrong5 savers
• Your Solution Doesn't Know Your Problem Exists5 savers
• Writing one sentence per line | Derek Sivers5 savers
• From fear to excitement — LessWrong5 savers
• Current AIs seem pretty misaligned to me4 savers
• Tempering hardcoreness - by Ajeya Cotra - Good Bones4 savers
• vivek on X: "how to be good at research" / X4 savers
• Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment4 savers
• The Bottleneck4 savers
• Substack4 savers
• Humans are not automatically strategic — LessWrong4 savers
• A playbook for field strategy - by Dewi Erwan4 savers
• Making Things Happen4 savers
• [2603.02202] Frontier Models Can Take Actions at Low Probabilities3 savers
• On The Independence Axiom — LessWrong3 savers
• Running away (Life Update) - Will Hathaway: Finding Out3 savers
• Life Hacking3 savers
• Short AI Timelines Aren’t Always Higher-Leverage3 savers
• Do you know your default shape?3 savers
• How do we (more) safely defer to AIs? — LessWrong3 savers
• The Human Skill That Eludes AI - The Atlantic3 savers
• Turns Out, You Can’t Just Bomb a Datacenter - by Sophie Kim2 savers
• Building something no one else can measure2 savers
• Fully autonomous robots are much closer than you think – Sergey Levine2 savers
• An Introduction to Exemplar Partitioning for Mechanistic Interpretability — LessWrong2 savers
• NYU Professor Teaches the Art of Writing (Ocean Vuong Interview) - YouTube2 savers