Submissions from lesswrong.com

		AI found 12 of 12 OpenSSL zero-days (lesswrong.com)
		2 points by greedo 13 hours ago \| past \| 1 comment
		Are We in a Continual Learning Overhang? (lesswrong.com)
		2 points by cubefox 6 days ago \| past \| discuss
		AI found 12 of 12 OpenSSL zero-days (lesswrong.com)
		2 points by jelsisi 6 days ago \| past \| discuss
		A Simple Method for Accelerating Grokking (lesswrong.com)
		2 points by vuciv 7 days ago \| past \| discuss
		Test your interpretability techniques by de-censoring Chinese models (lesswrong.com)
		2 points by allenleee 8 days ago \| past \| discuss
		How AI is learning to think in secret (lesswrong.com)
		2 points by jstanley 8 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 9 days ago \| past \| 1 comment
		Good if make prior after data instead of before (lesswrong.com)
		13 points by surprisetalk 9 days ago \| past \| 8 comments
		Does Pentagon Pizza Theory Work? (lesswrong.com)
		3 points by nreece 11 days ago \| past \| discuss
		How AI Is Learning to Think in Secret (lesswrong.com)
		3 points by mannykannot 12 days ago \| past \| 1 comment
		Dangerous capabilities can suddenly appear from gradual progress in AI (lesswrong.com)
		1 point by DalasNoin 14 days ago \| past
		Deep Learning as Program Synthesis (lesswrong.com)
		2 points by todsacerdoti 16 days ago \| past
		Shallow review of technical AI safety (2025) (lesswrong.com)
		1 point by ofou 16 days ago \| past
		Metacompilation (lesswrong.com)
		2 points by Antibabelic 16 days ago \| past
		Evidence that METR may be underestimating LLM time horizons (lesswrong.com)
		1 point by aorobin 17 days ago \| past
		Reflections on TA-ing Harvard's first AI safety course (lesswrong.com)
		2 points by sebg 21 days ago \| past
		Lies, Damned Lies and Proofs: Formal Methods Are Not Slopless (lesswrong.com)
		94 points by OgsyedIE 22 days ago \| past \| 44 comments
		The Exit (lesswrong.com)
		3 points by notarobot123 24 days ago \| past
		AI Teddy Bears: A Brief Investigation (lesswrong.com)
		3 points by surprisetalk 25 days ago \| past
		Humanity Wins (lesswrong.com)
		2 points by PhilosophyForAI 26 days ago \| past
		On Owning Galaxies (lesswrong.com)
		5 points by optimalsolver 28 days ago \| past
		An interactive toy model for exploring AI's effect on the labour market (lesswrong.com)
		1 point by ebursztein 29 days ago \| past
		Opinionated Takes on Meetups Organizing (lesswrong.com)
		2 points by surprisetalk 30 days ago \| past
		Insights into Claude Opus 4.5 from Pokémon (lesswrong.com)
		123 points by surprisetalk 30 days ago \| past \| 23 comments
		Chesterton's Fence (lesswrong.com)
		3 points by foster_nyman 30 days ago \| past
		You Will Be OK (lesswrong.com)
		3 points by walterbell 34 days ago \| past
		Straussian Memes (lesswrong.com)
		43 points by kp1197 35 days ago \| past \| 52 comments
		You Will Be OK (lesswrong.com)
		3 points by sebg 35 days ago \| past
		Eliezer s unteachable methods of sanity (lesswrong.com)
		1 point by prakashqwerty 37 days ago \| past
		Eliezer's Unteachable Methods of Sanity (lesswrong.com)
		2 points by paulpauper 45 days ago \| past
		More