@lesswrong LLMs can learn (some) multi-step reasoning on filler tokens #AI #MachineLearning #Rationality
@lesswrong What I might do if I were a high-schooler in 2027 #Rationality #ArtificialIntelligence #Philosophy
@lesswrong Fable 5.2 is Very, Very Paranoid #AI #Rationality #Philosophy
@lesswrong Quantified Cognition: A new Anki plugin #Rationality #Productivity #ArtificialIntelligence
@lesswrong You Don't Need Big Compute to Research Big Systems #Rationality #ArtificialIntelligence #Research
@lesswrong Vibe-Explaining Diagonalisation #Rationality #Science #Philosophy
@lesswrong Critique of Roman Yampolskiy's impossibility proofs #ArtificialIntelligence #Rationality #Philosophy
@lesswrong How I'm thinking about different types of automated alignment #ArtificialIntelligence #Rationality #Philosophy
@lesswrong Transfinite Procrastination #Rationality #Philosophy #DecisionMaking
@astral_codex_ten Escaping The "Outside Criticism" Trap #Psychology #Rationality #Statistics
@lesswrong Modern LLMs Don't Know What Yudkowsky and Soares Think of Them #ArtificialIntelligence #Rationality #Philosophy
@lesswrong Discussion with Claude on AI and global warming #ArtificialIntelligence #Rationality #Philosophy
@lesswrong There is no such thing as Neutral #Philosophy #Rationality #DecisionMaking
@lesswrong Reducing RL Pressure on Frontier Models: Four Approaches #ArtificialIntelligence #Rationality #Philosophy
@lesswrong False faced: can a simple classifier tell when a model is manipulating its activations to evade probes? #Rationality #ArtificialIntelligence #Philosophy
@lesswrong What Can AI Welfare Buy Without Consciousness? #AI #Philosophy #Rationality
@lesswrong San Francisco Rationalist Dinner #Rationality #Philosophy #Science
@lesswrong We don't understand whether GDM intentionally trains on CoT #ArtificialIntelligence #Rationality #Science
@lesswrong Please de-AI your life - part 1: daily conversations #ArtificialIntelligence #Philosophy #Rationality
@lesswrong I don't use AI #Rationality #ArtificialIntelligence #Philosophy
@lesswrong Hypotheses for causes of Claudisms in Claudist dialect of language #Rationality #ArtificialIntelligence #Philosophy
@lesswrong Fluid org boundaries with AI? #ArtificialIntelligence #Rationality #Future
@lesswrong Have you considered Actually Trying? #Rationality #Philosophy #DecisionMaking
@lesswrong Claude Fable 5.2 can do "weight-space-programming" about as well as GPT-6 Astra #Rationality #ArtificialIntelligence #Philosophy
@lesswrong Do Not Get Us on the No Fly List #Rationality #Philosophy #Science
@lesswrong AIFP: Looks Like the Intelligence Explosion Will Happen in 2027 After All #ArtificialIntelligence #Rationality #Philosophy
@lesswrong Which state AGs are ready to be proactive on AI? #ArtificialIntelligence #Rationality #Policy
@lesswrong AISF Day 1 Strategy Course Pre-Notes #Rationality #ArtificialIntelligence #Philosophy
@lesswrong Need for Speed #Rationality #ArtificialIntelligence #Philosophy
@lesswrong Nvidia CEO Jensen Huang Had an Affair With a Chinese Spy #Rationality #ArtificialIntelligence #Philosophy
@lesswrong Application open for CLR Fundamentals Program Autumn 2026 #Rationality #ArtificialIntelligence #Philosophy
@lesswrong Measure Optimal AI Share of Labor Costs Instead of AI or Human-Only Performance #Rationality #ArtificialIntelligence #Philosophy
@lesswrong Misaligned Models Still Recognise When Their Responses Are Harmful. Can Training Make Them Care? #Rationality #ArtificialIntelligence #Philosophy
@lesswrong Lightcone Commons: what I funded and why #Rationality #AI #Philosophy
@lesswrong Live disagreements with people around me #Rationality #Philosophy #DecisionMaking
@lesswrong Eyesight as a replicator, with genes as its vehicle #Rationality #Science #Philosophy
@lesswrong Lightcone Commons: Round 1 complete, Round 2 underway! #Rationality #ArtificialIntelligence #Philosophy
@lesswrong Epistemic Sudden Death #Rationality #Philosophy #DecisionMaking
@lesswrong A Circularity at the Heart of Safety Assurance #Rationality #ArtificialIntelligence #Philosophy
@lesswrong My Paranoid Coding Machine Setup #Tech #Programming #Rationality