Submissions from lesswrong.com

		AI found 12 OpenSSL zero-days (lesswrong.com)
		24 points by theptip 1 day ago \| past \| 1 comment
		Are there lessons from high-reliability engineering for AGI safety? (lesswrong.com)
		1 point by Gathering6678 1 day ago \| past \| discuss
		Responsible Scaling Policy v3 (lesswrong.com)
		1 point by ndr 2 days ago \| past \| discuss
		Great Mathematicians on Math Competitions(2010) (lesswrong.com)
		1 point by o4c 3 days ago \| past \| discuss
		Life at the Frontlines of Demographic Collapse (lesswrong.com)
		4 points by reducesuffering 5 days ago \| past \| 1 comment
		"Pinky Promise Diplomacy" Once Stopped a War in the Middle East (lesswrong.com)
		2 points by positivesum 5 days ago \| past \| discuss
		Childhoods of Exceptional People (2023) (lesswrong.com)
		1 point by Kinrany 9 days ago \| past \| discuss
		AI found 12 of 12 OpenSSL zero-days (lesswrong.com)
		8 points by AndrewDucker 9 days ago \| past \| 8 comments
		My journey to the microwave alternate timeline (lesswrong.com)
		382 points by jstanley 10 days ago \| past \| 191 comments
		Notes on International Klein Blue (lesswrong.com)
		4 points by mhb 11 days ago \| past \| discuss
		Why I'm Worried About Job Loss and Thoughts on Comparative Advantage (lesswrong.com)
		84 points by cubefox 11 days ago \| past \| 122 comments
		Spectral Signatures of Gradual Disempowerment (lesswrong.com)
		1 point by OgsyedIE 17 days ago \| past
		To be well-calibrated is to be punctual (lesswrong.com)
		2 points by surprisetalk 18 days ago \| past
		Google Translate apparently vulnerable to prompt injection (lesswrong.com)
		59 points by julkali 21 days ago \| past \| 3 comments
		AI found 12 of 12 OpenSSL zero-days (lesswrong.com)
		2 points by greedo 23 days ago \| past \| 1 comment
		52.5% of Moltbook posts show desire for self-improvement (lesswrong.com)
		1 point by one-2 26 days ago \| past
		Are We in a Continual Learning Overhang? (lesswrong.com)
		2 points by cubefox 29 days ago \| past
		AI found 12 of 12 OpenSSL zero-days (lesswrong.com)
		2 points by jelsisi 29 days ago \| past
		A Simple Method for Accelerating Grokking (lesswrong.com)
		2 points by vuciv 29 days ago \| past
		Test your interpretability techniques by de-censoring Chinese models (lesswrong.com)
		2 points by allenleee 30 days ago \| past
		How AI is learning to think in secret (lesswrong.com)
		2 points by jstanley 31 days ago \| past \| 1 comment
		AI discovers 12 of 12 OpenSSL zero-days (while curl cancelled its bug bounty) (lesswrong.com)
		7 points by excited-dev-11 31 days ago \| past \| 1 comment
		Good if make prior after data instead of before (lesswrong.com)
		13 points by surprisetalk 32 days ago \| past \| 9 comments
		Does Pentagon Pizza Theory Work? (lesswrong.com)
		3 points by nreece 33 days ago \| past
		How AI Is Learning to Think in Secret (lesswrong.com)
		3 points by mannykannot 35 days ago \| past \| 1 comment
		Dangerous capabilities can suddenly appear from gradual progress in AI (lesswrong.com)
		1 point by DalasNoin 37 days ago \| past
		Deep Learning as Program Synthesis (lesswrong.com)
		2 points by todsacerdoti 39 days ago \| past
		Shallow review of technical AI safety (2025) (lesswrong.com)
		1 point by ofou 39 days ago \| past
		Metacompilation (lesswrong.com)
		2 points by Antibabelic 39 days ago \| past
		Evidence that METR may be underestimating LLM time horizons (lesswrong.com)
		1 point by aorobin 40 days ago \| past
		More