Sudarsh K

on the atlas — 166

• Dionysian Futurism - Jeff Giesea3 savers
• From Beer Bottle to Arrowhead1 savers
• [2312.06942] AI Control: Improving Safety Despite Intentional Subversion3 savers
• Why We Need Continual Learning | Andreessen Horowitz5 savers
• Verified Machine Learning Infrastructure: Formal Methods for Trustworthy Artificial Intelligence Deployment | RAND1 savers
• Adaptive optics1 savers
• sophism5 savers
• Bits per Spike as a Betting Game · neurostatsblog1 savers
• Yitang_Zhang1 savers
• Bad Problems Don't Stop Being Bad Because Somebody's Wrong About Fault Analysis — LessWrong3 savers
• Ji-Ha's Blog1 savers
• The Life Goals of Dead People - by Ozy Brennan1 savers
• What Vegetable Are You?1 savers
• ARENA 6.0 Impact Report — LessWrong1 savers
• Whole Brain Emulation as an Anchor for AI Welfare - Benjamin Sturgeon website1 savers
• The Stanford Freshmen Who Think They Rule the World - The Atlantic6 savers
• Notes towards Neurostimulation and Mathematical Neuroscience1 savers
• Automated Alignment Researchers: Using large language models to scale scalable oversight \ Anthropic3 savers
• PiTorch: ML on Baremetal Raspberry Pis | projects6 savers
• 10 pieces of advice for children - Nina Panickssery3 savers
• Generative ML in chemistry is bottlenecked by synthesis2 savers
• Strangely, Matrix Multiplications on GPUs Run Faster When Given "Predictable" Data! [short]3 savers
• What is "good taste" in software engineering?4 savers
• Q-learning is not yet scalable6 savers
• Support (mathematics)1 savers
• Matryoshka Sparse Autoencoders — LessWrong2 savers
• TPU Deep Dive9 savers
• How the jax.jit() JIT compiler works in jax-js - Eric1 savers
• AI progress is about to speed up | Epoch AI4 savers
• My mind transformed completely, and there were some tradeoffs1 savers
• Embodying addiction: A predictive processing account - PMC1 savers
• Mind the Matrix: Looking Beyond Old Cells in Brain Aging1 savers
• An Age of Hyperabundance | Issue 47 | n+1 | Laura Preston2 savers
• The Webb Telescope Further Deepens the Biggest Controversy in Cosmology | Quanta Magazine1 savers
• Why Does Ozempic Cure All Diseases? - by Scott Alexander4 savers
• Curius / Onboarding2507 savers
• Child’s Play, by Sam Kriss75 savers
• Speed matters: Why working quickly is more important than it seems « the jsomers.net blog65 savers
• Milan Cvitkovic51 savers
• Reality has a surprising amount of detail49 savers
• AI 202749 savers
• Do Thing, Do One Thing45 savers
• Andy Matuschak43 savers
• 95%-ile isn't that good43 savers
• escaping flatland: career advice for CS undergrads41 savers
• Cities and Ambition39 savers
• Learning By Writing37 savers
• Defeating Nondeterminism in LLM Inference - Thinking Machines Lab37 savers
• The housing theory of everything - Works in Progress34 savers
• The Gap Map33 savers
• LoRA Without Regret - Thinking Machines Lab32 savers
• The Darker Side of Aaron Swartz | The New Yorker30 savers
• When AI builds itself \ Anthropic30 savers
• Ink & Switch29 savers
• Works in Progress28 savers
• The Persona Selection Model: Why AI Assistants might Behave like Humans28 savers
• Dynamicland27 savers
• https://cs.stanford.edu/~jsteinhardt/ResearchasaStochasticDecisionProcess.html26 savers
• On-Policy Distillation - Thinking Machines Lab26 savers
• Study Guide - LessWrong26 savers
• Do I Need to Go to University? -- colah's blog25 savers
• Making Deep Learning Go Faster25 savers
• I am rich and have no idea what to do with my life25 savers
• Please don't throw your mind away — LessWrong24 savers
• How to Optimize a CUDA Matmul Kernel for cuBLAS-like Performance: a Worklog23 savers
• Towards Monosemanticity: Decomposing Language Models With Dictionary Learning23 savers
• A heart of fire21 savers
• Chloe's Garden21 savers
• Notes on Managing ADHD21 savers
• 24 hours in an invisible epidemic20 savers
• Notes on Effective Altruism20 savers
• AI as Normal Technology | Knight First Amendment Institute20 savers
• An open letter to 56 people I know - by Sasha Chapin20 savers
• OpenAI Email Archives (from Musk v. Altman) — LessWrong19 savers
• Why Tool AIs Want to Be Agent AIs · Gwern.net18 savers
• 50 things I know - by Sasha Chapin - Sasha's 'Newsletter'18 savers
• Alignment is not solved but it increasingly looks solvable17 savers
• The Anthropic Hive Mind. As you’ve probably noticed, something… | by Steve Yegge | Feb, 2026 | Medium17 savers
• Did Claude 3 Opus align itself via gradient hacking? — LessWrong16 savers
• Bret Victor, beast of burden16 savers
• How To Understand Things - Nabeel S. Qureshi16 savers
• What are Diffusion Models? | Lil'Log16 savers
• Having Kids15 savers
• Deriving Muon15 savers
• 50 things I know - by Cate Hall - Useful Fictions15 savers
• Top Performers are Pathologically Ambitious - by Matt Beard15 savers
• Modular Manifolds - Thinking Machines Lab15 savers
• Tips for Empirical Alignment Research — AI Alignment Forum13 savers
• Universal Love, Said The Cactus Person13 savers
• DeepSeek-R112 savers
• Diffusion is spectral autoregression – Sander Dieleman12 savers
• EC05-Chen.dvi11 savers
• Could a Neuroscientist Understand a Microprocessor?11 savers
• We Induced Smells With Ultrasound11 savers
• You will be OK — LessWrong11 savers
• Surrender as a non-stupid life strategy11 savers
• The Shard Theory of Human Values10 savers
• A New Era of Midjourney10 savers
• On neural scaling and the quanta hypothesis10 savers
• Peritext: A CRDT for Rich-Text Collaboration9 savers