Submissions from lesswrong.com

		Paper Close Reading: "Why Language Models Hallucinate" (lesswrong.com)
		2 points by joozio 5 hours ago \| past \| discuss
		Estimates of the expected utility gain of AI Safety Research (lesswrong.com)
		1 point by joozio 9 hours ago \| past \| discuss
		What I like about MATS and Research Management (lesswrong.com)
		2 points by joozio 23 hours ago \| past \| discuss
		Predicting When RL Training Breaks Chain-of-Thought Monitorability (lesswrong.com)
		2 points by gmays 1 day ago \| past \| discuss
		AI Safety at the Frontier: Paper Highlights of February and March 2026 (lesswrong.com)
		2 points by joozio 1 day ago \| past \| discuss
		How to emotionally grasp the risks of AI Safety (lesswrong.com)
		3 points by joozio 2 days ago \| past \| discuss
		You can't imitation-learn how to continual-learn (lesswrong.com)
		2 points by paulpauper 3 days ago \| past \| discuss
		A Mirror Test for LLMs (lesswrong.com)
		2 points by gmays 3 days ago \| past \| discuss
		I'm Suing Anthropic for Unauthorized Use of My Personality (lesswrong.com)
		5 points by usrme 4 days ago \| past \| 2 comments
		Why did everything take so long? (lesswrong.com)
		2 points by jstanley 5 days ago \| past \| discuss
		The state of AI safety in four fake graphs (lesswrong.com)
		3 points by allenleee 5 days ago \| past \| discuss
		Gyre (lesswrong.com)
		3 points by jstanley 5 days ago \| past \| discuss
		Less Dead (lesswrong.com)
		2 points by paulpauper 6 days ago \| past \| discuss
		Using complex polynomials to approximate arbitrary continuous functions (2025) (lesswrong.com)
		1 point by measurablefunc 6 days ago \| past \| discuss
		The Terrarium (lesswrong.com)
		1 point by johnfn 6 days ago \| past \| discuss
		AI's capability improvements haven't come from it getting less affordable (lesswrong.com)
		3 points by gmays 6 days ago \| past \| discuss
		I am definitely missing the pre-AI writing era (lesswrong.com)
		322 points by joozio 7 days ago \| past \| 240 comments
		Stanley Milgram wasn't pessimistic enough about human nature? (lesswrong.com)
		7 points by paulpauper 7 days ago \| past \| 1 comment
		Anthropic Donations: Guesses and Uncertainties (lesswrong.com)
		2 points by joozio 7 days ago \| past \| discuss
		Folie à Machine: LLMs and Epistemic Capture (lesswrong.com)
		2 points by joozio 7 days ago \| past \| discuss
		Tracking (Expert/Influential) Predictions about AI (lesswrong.com)
		3 points by joozio 8 days ago \| past \| discuss
		You can't imitation-learn how to continual-learn (lesswrong.com)
		11 points by supermdguy 9 days ago \| past \| discuss
		The Terrarium (lesswrong.com)
		2 points by cubefox 9 days ago \| past \| discuss
		A Tom-Inspired Agenda for AI Safety Research (lesswrong.com)
		2 points by joozio 13 days ago \| past \| 1 comment
		Which types of AI alignment research are most likely to be good for all sentien (lesswrong.com)
		3 points by joozio 13 days ago \| past \| discuss
		The Distaff Texts (lesswrong.com)
		1 point by paulpauper 15 days ago \| past
		The Hot Mess Paper Conflates Three Distinct Failure Modes (lesswrong.com)
		2 points by joozio 16 days ago \| past
		Broad Timelines (lesswrong.com)
		2 points by gmays 16 days ago \| past
		Tacit Knowledge Videos on Every Subject (lesswrong.com)
		1 point by sebg 18 days ago \| past
		LessWrong Policy on LLM Use (lesswrong.com)
		10 points by xpe 21 days ago \| past \| 4 comments
		More