Neil Rathi

on the atlas — 61

• Prince - Just My Imagination 1988 - YouTube1 savers
• "Creep" - Prince at Coachella 2008 (Uploaded via Permission from Radiohead & NPG Music Publishing) - YouTube1 savers
• Mock Orange | The Poetry Foundation1 savers
• Frank Ocean - Wiseman (live in Paris) - YouTube1 savers
• Jamie xx | Boiler Room x Young Turks: London - YouTube1 savers
• A. G. Cook Boiler Room DJ Set - YouTube1 savers
• [2604.22082] Removing Sandbagging in LLMs by Training with Weak Supervision5 savers
• ErostheBittersweetEssay.pdf1 savers
• web.mit.edu/daveg/Text/poetry/Manifest:MFLF5 savers
• King Krule - Out Getting Ribs live (Hyères) 2011 - YouTube1 savers
• Anarchist Calisthenics, by James C. Scott1 savers
• Winter Stars | The Poetry Foundation1 savers
• Youtube duet: Miles Davis improvising on LCD Soundsystem - YouTube3 savers
• Bitter Lessons from Distillation Robustifies Unlearning4 savers
• The Human Skill That Eludes AI - The Atlantic3 savers
• Odd couple: How co-op and Greek life shape campus culture1 savers
• Yanartaş2 savers
• Caravan played by Monk in Berlin, 1969 - YouTube1 savers
• Branford Marsalis - A Love Supreme, live at Amsterdam -2003- - YouTube1 savers
• Lynn Adib - Sona | Sofar Beirut - YouTube1 savers
• Her’s - Full Session | Live at Paste Studios NYC [Paste Rewind, 2018] - YouTube1 savers
• [2602.05910] Chunky Post-Training: Data Driven Failures of Generalization1 savers
• When a Noma Chef Visits China’s Fermentation City (S2, E3) - YouTube2 savers
• [Jan 7 2026] nanochat miniseries v1 · karpathy/nanochat · Discussion #4201 savers
• How hard is it to inoculate against misalignment generalization? — LessWrong2 savers
• You Have Only X Years To Escape Permanent Moon Ownership1 savers
• Reflections on 2025 - Samuel Albanie7 savers
• confessions_paper.pdf2 savers
• INTELLIGENCE2 savers
• Anatomy of a Modern Finetuning API4 savers
• bo on X: "performative curius highlighting" / X4 savers
• Child’s Play, by Sam Kriss75 savers
• 2025 letter | Dan Wang62 savers
• The Persona Selection Model: Why AI Assistants might Behave like Humans28 savers
• The Intelligence Curse24 savers
• Did Claude 3 Opus align itself via gradient hacking? — LessWrong16 savers
• Stanford’s War on Social Life14 savers
• Alignment remains a hard, unsolved problem — LessWrong14 savers
• You will be OK — LessWrong11 savers
• The realities of being a pop star. - by charli xcx10 savers
• Existential risk, AI, and the inevitable turn in human history - Marginal REVOLUTION9 savers
• RLHF Book by Nathan Lambert8 savers
• Turning 20 in the probable pre-apocalypse — LessWrong8 savers
• An Ambitious Vision for Interpretability — AI Alignment Forum8 savers
• davidbau.com In Defense of Curiosity7 savers
• What Would Non-Linear Features Actually Look Like? | Liv Gorton7 savers
• llm assistant personas seem increasingly incoherent (some subjective observations) — LessWrong7 savers
• A Pragmatic Vision for Interpretability — AI Alignment Forum6 savers
• What 2026 looks like - LessWrong6 savers
• Oversight Assistants: Turning Compute into Understanding5 savers
• Building Technology to Drive AI Governance5 savers
• Searching for God in Silicon Valley - by Avital Balwit5 savers
• Thinking Machines Corporation4 savers
• [2604.16812] Introspection Adapters: Training LLMs to Report Their Learned Behaviors4 savers
• Self-Fulfilling Misalignment Data Might Be Poisoning Our AI Models4 savers
• The least understood driver of AI progress | Epoch AI3 savers
• Opinion | When A.I. Took My Job, I Bought a Chain Saw - The New York Times3 savers
• Anne Carson · Beware the man whose handwriting sways like a reed in the wind3 savers
• Were classical statues painted horribly? - Works in Progress Magazine2 savers
• The West Village Girls Are Changing How the World Sees NYC2 savers
• How Should AI Liability Work? (Part I) - by Dean W. Ball2 savers