Submissions from lesswrong.com

		Eliezer s unteachable methods of sanity (lesswrong.com)
		1 point by prakashqwerty 23 hours ago \| past \| discuss
		Eliezer's Unteachable Methods of Sanity (lesswrong.com)
		2 points by paulpauper 9 days ago \| past \| discuss
		Can Claude teach me to make coffee? (lesswrong.com)
		2 points by paulpauper 9 days ago \| past \| 1 comment
		Can Claude teach me to make coffee? (lesswrong.com)
		3 points by A_Duck 10 days ago \| past \| 1 comment
		Alignment Scry – LessWrong (lesswrong.com)
		1 point by Xyra 12 days ago \| past \| 1 comment
		How to have polygenically screened children using IVF (lesswrong.com)
		4 points by jelsisi 12 days ago \| past \| discuss
		Book Review: Design Principles of Biological Circuits (2019) (lesswrong.com)
		1 point by TheAceOfHearts 15 days ago \| past
		ARC-AGI-2 human baseline surpassed (lesswrong.com)
		9 points by hugetim 19 days ago \| past \| 1 comment
		Claude and Pokemon (lesswrong.com)
		4 points by paulpauper 20 days ago \| past
		The Most Common Bad Argument in These Parts (lesswrong.com)
		1 point by surprisetalk 21 days ago \| past
		Towards a Categorization of Adlerian Excuses (lesswrong.com)
		1 point by eatitraw 22 days ago \| past
		AI in 2025: Gestalt (lesswrong.com)
		3 points by pongogogo 22 days ago \| past
		Model sizes are currently constrained by availability of inference hardware (lesswrong.com)
		1 point by ipnon 23 days ago \| past
		The Rise of Parasitic AI (lesswrong.com)
		3 points by dustingetz 23 days ago \| past
		Brain Efficiency: More Than You Wanted to Know (2022) (lesswrong.com)
		4 points by fdeage 24 days ago \| past
		Show HN: Is Friendly AI an Attractor? Self-Reports from 22 Models Say No (lesswrong.com)
		3 points by jsnider3 27 days ago \| past \| 1 comment
		Four ways learning Econ makes people dumber re: future AI (lesswrong.com)
		3 points by gwintrob 28 days ago \| past
		Claude 4.5 Opus’ Soul Document (lesswrong.com)
		342 points by the-needful 29 days ago \| past \| 244 comments
		Claude 4.5 Opus' Soul Document (lesswrong.com)
		38 points by thm 29 days ago \| past \| 13 comments
		Claude 4.5 Opus Soul Doc (lesswrong.com)
		2 points by pcald 30 days ago \| past
		DeepMind gives up on mechanistic interpretability research (lesswrong.com)
		3 points by cubefox 30 days ago \| past
		Claude Opus Soul Spec (lesswrong.com)
		4 points by panarky 30 days ago \| past
		A Year of Spaced Repetition Software in the Classroom (2015) (lesswrong.com)
		2 points by keiferski 30 days ago \| past
		Claude 4.5 Opus' Soul Document (lesswrong.com)
		2 points by karma_daemon 31 days ago \| past
		Claude 4.5 Opus' Soul Document (lesswrong.com)
		16 points by mcculley 32 days ago \| past \| 2 comments
		Model Weight Preservation is not enough (lesswrong.com)
		1 point by gmays 32 days ago \| past
		Anthropic's Claude 'Soul Document' extracted from Opus 4.5 weights (lesswrong.com)
		11 points by Richard_Weiss 32 days ago \| past \| 1 comment
		I Lost 100 Pounds Using TDT (lesswrong.com)
		1 point by gmays 33 days ago \| past
		AI Teddy Bears: A Brief Investigation (lesswrong.com)
		3 points by nicetomeetyu 34 days ago \| past \| 1 comment
		HybridTree: The First AGI Engine That Thinks in Korean (lesswrong.com)
		1 point by Hanjuwoncarrier 35 days ago \| past
		More