Submissions from lesswrong.com

		You can't imitation-learn how to continual-learn (lesswrong.com)
		10 points by supermdguy 16 hours ago \| past \| discuss
		The Terrarium (lesswrong.com)
		2 points by cubefox 1 day ago \| past \| discuss
		A Tom-Inspired Agenda for AI Safety Research (lesswrong.com)
		2 points by joozio 4 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 5 days ago \| past \| discuss
		The Distaff Texts (lesswrong.com)
		1 point by paulpauper 7 days ago \| past \| discuss
		The Hot Mess Paper Conflates Three Distinct Failure Modes (lesswrong.com)
		2 points by joozio 7 days ago \| past \| discuss
		Broad Timelines (lesswrong.com)
		2 points by gmays 8 days ago \| past \| discuss
		Tacit Knowledge Videos on Every Subject (lesswrong.com)
		1 point by sebg 9 days ago \| past \| discuss
		LessWrong Policy on LLM Use (lesswrong.com)
		10 points by xpe 13 days ago \| past \| 4 comments
		Never Go Full Kelly (lesswrong.com)
		3 points by pinkmuffinere 13 days ago \| past \| 1 comment
		The ~fifth~ fourth postulate of decision theory (On the Independence Axiom) (lesswrong.com)
		2 points by sieste 13 days ago \| past \| discuss
		High Grow Market Equilibrium After the Singularity (lesswrong.com)
		2 points by gmays 15 days ago \| past
		Selectively reducing eval awareness and murder in Gemma 3 27B via steering (lesswrong.com)
		3 points by gmays 16 days ago \| past
		Gemma Needs Help (lesswrong.com)
		38 points by pr337h4m 18 days ago \| past \| 1 comment
		The truth behind the 2026 J.P. Morgan Healthcare Conference (lesswrong.com)
		1 point by surprisetalk 18 days ago \| past
		Models have some pretty funny attractor states (lesswrong.com)
		3 points by semiquaver 19 days ago \| past
		Shaping the exploration of the motivation-space matters for AI safety (lesswrong.com)
		1 point by gmays 19 days ago \| past
		Large-Scale Online Deanonymization with LLMs (lesswrong.com)
		1 point by cubefox 19 days ago \| past
		The optimal age to freeze eggs is 19 (lesswrong.com)
		91 points by surprisetalk 19 days ago \| past \| 135 comments
		To the Polypropylene Makers (lesswrong.com)
		88 points by raldi 21 days ago \| past \| 27 comments
		Sacred Values of Future AIs (lesswrong.com)
		1 point by gmays 23 days ago \| past
		Refusal in LLMs is mediated by a single direction (lesswrong.com)
		2 points by rzk 23 days ago \| past
		Models have some pretty funny attractor states (lesswrong.com)
		3 points by debesyla 24 days ago \| past
		Canada Lost Its Measles Elimination Status Because Few Nurses Speak Low German (lesswrong.com)
		5 points by surprisetalk 26 days ago \| past \| 2 comments
		AI found 12 OpenSSL zero-days (lesswrong.com)
		24 points by theptip 29 days ago \| past \| 1 comment
		Are there lessons from high-reliability engineering for AGI safety? (lesswrong.com)
		1 point by Gathering6678 30 days ago \| past
		Responsible Scaling Policy v3 (lesswrong.com)
		1 point by ndr 30 days ago \| past
		Great Mathematicians on Math Competitions(2010) (lesswrong.com)
		1 point by o4c 31 days ago \| past
		Life at the Frontlines of Demographic Collapse (lesswrong.com)
		4 points by reducesuffering 33 days ago \| past \| 1 comment
		"Pinky Promise Diplomacy" Once Stopped a War in the Middle East (lesswrong.com)
		2 points by positivesum 34 days ago \| past
		More