Yudhister Joel Kumar

on the atlas — 477

• Chernoff bound1 savers
• Sam_Zemurray1 savers
• [2501.16946] Gradual Disempowerment: Systemic Existential Risks from Incremental AI Development3 savers
• Making deals with early schemers — LessWrong2 savers
• The Artificial Self5 savers
• John Rawls2 savers
• Tensor product1 savers
• Home | seL41 savers
• Working through a small tiling result — LessWrong3 savers
• Metagaming matters for training, evaluation, and oversight2 savers
• A Straussian reading of The Adolescence of Technology | Zhengdong2 savers
• Open-minded updatelessness — LessWrong1 savers
• Nelson Elhage1 savers
• Thoughts on Updatelessness – The Universe from an Intentional Stance1 savers
• [2310.17813] A Spectral Condition for Feature Learning1 savers
• Bonsai-demo/1-bit-bonsai-8b-whitepaper.pdf at main · PrismML-Eng/Bonsai-demo1 savers
• State of Brain Emulation Report 2025 | Research Overview1 savers
• There should be ‘general managers’ for more of the world’s important problems6 savers
• The_Final_Offshoring.pdf1 savers
• Understanding the Neural Tangent Kernel – EigenTales3 savers
• Quantifying Truesight With SAEs · Gwern.net2 savers
• Patrick Collison on programming languages, AI, and Stripe's biggest engineering decisions - YouTube1 savers
• Effective Startup Ideation4 savers
• arg min | Ben Recht | Substack1 savers
• Building Technology to Drive AI Governance5 savers
• Tim Roughgarden's Lecture Notes1 savers
• A Travelogue from India and China2 savers
• Different senses in which two AIs can be “the same” — LessWrong1 savers
• MatX: High-throughput chips for LLMs2 savers
• Think Tanks Have Defeated Democracy6 savers
• The Origins and Motivations of Univalent Foundations - Ideas | Institute for Advanced Study1 savers
• Deontology and virtue ethics as "effective theories" of consequentialist ethics — LessWrong2 savers
• Conversational Cultures: Combat vs Nurture (V2) — LessWrong1 savers
• Agam Bhatia1 savers
• Bodega Bay Nuclear Power Plant1 savers
• [2604.06366] Stochastic Gradient Descent in the Saddle-to-Saddle Regime of Deep Linear Networks1 savers
• Role-playing vs Self-modelling — LessWrong2 savers
• Harvard University1 savers
• Thomas Nagel1 savers
• (PDF) A Fine is a Price1 savers
• An Alignment Journal: Features and policies · Alignment Journal Blog1 savers
• 2e9f9cde1b709281a06dd14f679e4c51-Paper-Conference.pdf1 savers
• An Alignment Journal: Features and policies — LessWrong1 savers
• Beliefs are Chosen to Serve Goals — LessWrong3 savers
• Inference to the Best Explanation (article)1 savers
• Spiral Dynamics1 savers
• Dialogue: Is there a Natural Abstraction of Good? — LessWrong1 savers
• Smart Policy: Cognitive Enhancement and the Public Interest1 savers
• The Unilateralist’s Curse and the Case for a Principle of Conformity1 savers
• Reformative Hypocrisy, and Paying Close Enough Attention to Selectively Reward It. — LessWrong1 savers
• [2604.04891] Muon Dynamics as a Spectral Wasserstein Flow1 savers
• LLM Alignment, ethical and mathematical realism, and the most important actions in davidad's understanding — LessWrong1 savers
• College at Age Sixteen: What Is Intelligence For?2 savers
• Does novel understanding imply novel agency / values?1 savers
• Mathematics for humans1 savers
• Gardens of the Soul — Laura Deming5 savers
• microgpt5 savers
• On The Independence Axiom — LessWrong3 savers
• The Coastal Elites Are Right, Actually - by A.M. Hickman1 savers
• The Shard Theory of Human Values10 savers
• 4. Sets and Functions — Mathematics in Lean 0.1 documentation1 savers
• mathematicians.pdf1 savers
• How to win a best paper award (or, an opinionated take on how to do important research)24 savers
• The Gap Map33 savers
• [2308.12108] The Local Learning Coefficient: A Singularity-Aware Complexity Measure2 savers
• Which Future?1 savers
• Singular Learning Theory Seminar1 savers
• We were wrong about convergence2 savers
• I Would Have Solved Alignment, But I Was Worried That Would Advance Timelines — LessWrong1 savers
• Mathematics in the Library of Babel — Daniel Litt5 savers
• My journey to the microwave alternate timeline — LessWrong3 savers
• Why You Don’t Believe in Xhosa Prophecies — LessWrong3 savers
• matrix-book.pdf1 savers
• In (highly contingent!) defense of interpretability-in-the-loop ML training — AI Alignment Forum2 savers
• [2601.21571] Shaping capabilities with token-level data filtering4 savers
• Basics of How Not to Die — LessWrong1 savers
• Moltbook is the most interesting place on the internet right now8 savers
• On Agency | Sebastian Farquhar1 savers
• Stuff you should have been taught in college but weren’t – Casey Handmer's blog8 savers
• Base Camp for Mt. Ethics1 savers
• On “compilation errors” in mathematical reading, and how to resolve them | What's new1 savers
• On Doubling7 savers
• An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forum2 savers
• How Hangzhou Spawned Deepseek and Unitree1 savers
• An Opinionated Guide to Using Anki Correctly — LessWrong3 savers
• [1805.00909] Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review1 savers
• Relentlessly Resourceful3 savers
• Did California's Fast Food Minimum Wage Reduce Employment? | NBER1 savers
• Arc Institute’s first virtual cell model: <span style="font-variant: small-caps">S<span style="font-weight: bolder">tate</span></span> | Arc Institute2 savers
• What is AIXI?1 savers
• leogao's Shortform — LessWrong3 savers
• Fact Finding: Attempting to Reverse-Engineer Factual Recall on the Neuron Level (Post 1) — AI Alignment Forum1 savers
• Diffusion is not necessarily Spectral Autoregression | Fabian Falck1 savers
• The Importance of Diminishing Returns - Econlib1 savers
• Wolfgang Schwarz :: On Functional Decision Theory2 savers
• [1508.04145] Reflective Oracles: A Foundation for Classical Game Theory1 savers
• Shtetl-Optimized » Blog Archive » Umeshisms8 savers
• Clarifying and predicting AGI — LessWrong1 savers
• Attribution-based parameter decomposition — LessWrong1 savers
• Arnold's proof of Abel-Ruffini2 savers