@lesswrong Linkpost: Can a million AI agents create superintelligence? #AI #Superintelligence #Rationality
@lesswrong Dinners for AI Safety #AISafety #AI #Rationality
@lesswrong Organizing a Van to EA Global #Rationality #EA #Organization
@lesswrong Updatelessness explained #Rationality #AI #Philosophy
@astral_codex_ten Against Against Handover #Rationality #Thinking #Philosophy
@lesswrong A brief(ish) introduction to LM psychology #AI #Psychology #Rationality
@lesswrong Agent Action Steering #AI #Rationality #DecisionMaking
@lesswrong VPD's Evaluation Adversary Finds Systematic Defects in the Released Decomposition #AI #Rationality #Research
@effective_altruism_forum Cluelessness is Zeno's paradox for EAs #EffectiveAltruism #Philosophy #Rationality
@lesswrong There Will Be Hells #Rationality #Philosophy #AI
@lesswrong Cluelessness is Zeno's paradox for EAs #Rationality #AI #Philosophy
@lesswrong Firewalls for the Mind Before We Need Them #Rationality #AI #Philosophy
@lesswrong Human or AI? Baroque Music Quiz Results & Analysis #AI #Music #Rationality
@lesswrong Annotations for AI Doompop #AI #Rationality #Philosophy
@lesswrong Restarting/reformulating the practice of shared sacredness experiences for secular people by developing a passive haptic feedback learning interface to rapidly teach partimento - the historical method used for training church musicians in Naples. #Rationality #AI #Philosophy
@lesswrong Why Clean Neurons Are Not Enough #AI #Philosophy #Rationality
@lesswrong A Tourist Mathematician's Apologia: Living in a Human-AGI World #AI #Rationality #Philosophy
@lesswrong Red-teaming multi-agent attacks for loss-of-control risks #AI #Rationality #Security
@lesswrong Human vs AI in Go in 2026: Lessons for superintelligence? #AI #Superintelligence #Rationality
@lesswrong Improving the flow of interesting things #Rationality #AI #Philosophy
@lesswrong What do the other 80 percent mean? #Rationality #DecisionMaking #AI
@lesswrong GLM-5.1 Has ~Astra Level CoT Control #AI #MachineLearning #Rationality
@lesswrong Permanent underclass taxonomy #Philosophy #SocialScience #Rationality
@lesswrong How is "prosaic aligned AI" supposed to work? #AI #Rationality #Philosophy
@lesswrong AI as a Normal Technology should be a vision #AI #Technology #Rationality
@lesswrong Using AI to find good Manifund projects #AI #Rationality #Philanthropy
@lesswrong First Strike #Rationality #DecisionMaking #AI
@lesswrong Memes, not agents, are what will kill us #AI #Philosophy #Rationality
@lesswrong Capital Ownership Will Make You Go Crazy First #Economics #Psychology #Rationality
@lesswrong I Can See Everything #AI #Philosophy #Rationality
@lesswrong Reinforcement Learning is Probably Inconsistent with Ethics #AI #Ethics #Rationality
@lesswrong When AI Advice Shapes the Evidence It Later Interprets #AI #Rationality #DecisionMaking
@lesswrong More Capable Models Write Better Probe Evasion Prompts #AI #MachineLearning #Rationality
@lesswrong Examining AI Swarm Efficiency with the AI Futures Model #AI #Rationality #Modeling
@lesswrong Sorry, you are still dead #Rationality #Philosophy #AI
@lesswrong The Case for Building AI Safety Tools #AISafety #AI #Rationality
@lesswrong On Qwen, the J-lens readouts at the newline token reveal lies #AI #Rationality #LLM
@lesswrong Quick Thoughts on Overhang Arguments #Rationality #DecisionMaking #Philosophy
@lesswrong The Lightcone Needs You To Plan a Vacation #Rationality #DecisionMaking #AI
@lesswrong Disproving the SIA disproves the Fine-Tuning Argument and Boltzmann-brain-based arguments #Philosophy #Rationality #Science