Submissions from lesswrong.com

		Does Pentagon Pizza Theory Work? (lesswrong.com)
		1 point by nreece 21 minutes ago \| past \| discuss
		How AI Is Learning to Think in Secret (lesswrong.com)
		3 points by mannykannot 1 day ago \| past \| 1 comment
		Dangerous capabilities can suddenly appear from gradual progress in AI (lesswrong.com)
		1 point by DalasNoin 3 days ago \| past \| discuss
		Deep Learning as Program Synthesis (lesswrong.com)
		2 points by todsacerdoti 5 days ago \| past \| discuss
		Shallow review of technical AI safety (2025) (lesswrong.com)
		1 point by ofou 5 days ago \| past \| discuss
		Metacompilation (lesswrong.com)
		2 points by Antibabelic 5 days ago \| past \| discuss
		Evidence that METR may be underestimating LLM time horizons (lesswrong.com)
		1 point by aorobin 6 days ago \| past \| discuss
		Reflections on TA-ing Harvard's first AI safety course (lesswrong.com)
		2 points by sebg 10 days ago \| past \| discuss
		Lies, Damned Lies and Proofs: Formal Methods Are Not Slopless (lesswrong.com)
		94 points by OgsyedIE 11 days ago \| past \| 44 comments
		The Exit (lesswrong.com)
		3 points by notarobot123 13 days ago \| past \| discuss
		AI Teddy Bears: A Brief Investigation (lesswrong.com)
		3 points by surprisetalk 14 days ago \| past
		Humanity Wins (lesswrong.com)
		2 points by PhilosophyForAI 15 days ago \| past
		On Owning Galaxies (lesswrong.com)
		5 points by optimalsolver 17 days ago \| past
		An interactive toy model for exploring AI's effect on the labour market (lesswrong.com)
		1 point by ebursztein 18 days ago \| past
		Opinionated Takes on Meetups Organizing (lesswrong.com)
		2 points by surprisetalk 19 days ago \| past
		Insights into Claude Opus 4.5 from Pokémon (lesswrong.com)
		123 points by surprisetalk 19 days ago \| past \| 23 comments
		Chesterton's Fence (lesswrong.com)
		3 points by foster_nyman 19 days ago \| past
		You Will Be OK (lesswrong.com)
		3 points by walterbell 23 days ago \| past
		Straussian Memes (lesswrong.com)
		43 points by kp1197 24 days ago \| past \| 52 comments
		You Will Be OK (lesswrong.com)
		3 points by sebg 24 days ago \| past
		Eliezer s unteachable methods of sanity (lesswrong.com)
		1 point by prakashqwerty 25 days ago \| past
		Eliezer's Unteachable Methods of Sanity (lesswrong.com)
		2 points by paulpauper 34 days ago \| past
		Can Claude teach me to make coffee? (lesswrong.com)
		2 points by paulpauper 34 days ago \| past \| 1 comment
		Can Claude teach me to make coffee? (lesswrong.com)
		3 points by A_Duck 35 days ago \| past \| 1 comment
		Alignment Scry – LessWrong (lesswrong.com)
		1 point by Xyra 36 days ago \| past \| 1 comment
		How to have polygenically screened children using IVF (lesswrong.com)
		4 points by jelsisi 37 days ago \| past
		Book Review: Design Principles of Biological Circuits (2019) (lesswrong.com)
		1 point by TheAceOfHearts 40 days ago \| past
		ARC-AGI-2 human baseline surpassed (lesswrong.com)
		9 points by hugetim 44 days ago \| past \| 1 comment
		Claude and Pokemon (lesswrong.com)
		4 points by paulpauper 45 days ago \| past
		The Most Common Bad Argument in These Parts (lesswrong.com)
		1 point by surprisetalk 46 days ago \| past
		More