Submissions from lesswrong.com

		P(Kill-Switch\|Detection) (lesswrong.com)
		1 point by kp1197 3 hours ago \| past \| discuss
		Watch AI materials-science and bioscience abilities closely (lesswrong.com)
		39 points by joozio 11 hours ago \| past \| 49 comments
		Another Slice of Swiss Cheese for Untrusted Monitoring (lesswrong.com)
		2 points by joozio 15 hours ago \| past \| discuss
		Astra and Fable still hack on simple variants of alignment evals from 2025 (lesswrong.com)
		464 points by Levitating 1 day ago \| past \| 227 comments
		The Talker Does Not Control the Doer (In Current AIs) (lesswrong.com)
		1 point by jstanley 1 day ago \| past \| 1 comment
		An interesting anecdote from our Hacker Opus work (lesswrong.com)
		2 points by yurivish 1 day ago \| past \| discuss
		How My Students Think About AI (lesswrong.com)
		51 points by paulpauper 3 days ago \| past \| 10 comments
		Adaptive Agentic Worms Are Here (lesswrong.com)
		2 points by speckx 5 days ago \| past \| discuss
		Astra and Fable still hack on simple variants of alignment evals from 2025 (lesswrong.com)
		2 points by yurivish 6 days ago \| past \| discuss
		Interpreting GPT: The Logit Lens (lesswrong.com)
		2 points by Bluestein 6 days ago \| past \| discuss
		From safety research prompt to cross-model universal jailbreak (lesswrong.com)
		2 points by gmays 7 days ago \| past \| discuss
		My Students Think About AI (lesswrong.com)
		5 points by alphabetatango 10 days ago \| past \| 1 comment
		Asking agents to make money to survive (lesswrong.com)
		4 points by paraschopra 10 days ago \| past \| discuss
		What is nueralese and why is it bad (lesswrong.com)
		77 points by tristanMatthias 10 days ago \| past \| 59 comments
		How concerned should we be about Astra's recurrent architecture? (lesswrong.com)
		151 points by yurivish 11 days ago \| past \| 129 comments
		METR Researcher Thomas Kwa Hired by OpenAI (lesswrong.com)
		1 point by qlte 11 days ago \| past \| discuss
		The Library of Scott Alexandria (lesswrong.com)
		4 points by benatkin 11 days ago \| past \| 1 comment
		Models may behave differently in graded episode (lesswrong.com)
		2 points by ddp26 12 days ago \| past \| discuss
		AGI and the Efficient Market Hypothesis (2023) (lesswrong.com)
		2 points by Metacelsus 13 days ago \| past \| 1 comment
		How My Students Think About AI (lesswrong.com)
		5 points by pella 13 days ago \| past \| 1 comment
		P(Kill-Switch\|Detection) (lesswrong.com)
		2 points by kp1197 14 days ago \| past
		Starting AI Safety Study Group to Do Arena Curriculum (lesswrong.com)
		2 points by joozio 14 days ago \| past
		Cooperating with aliens and AGIs: An ECL explainer (lesswrong.com)
		3 points by Bluestein 19 days ago \| past
		Prompt Sufficiency: A Missive for the Managerial Class (lesswrong.com)
		1 point by kp1197 22 days ago \| past
		We Must Remember That Our World Contains Hell (lesswrong.com)
		1 point by paulpauper 24 days ago \| past
		LLMs are (still) mostly powered by imitative learning, not RL (lesswrong.com)
		3 points by wslh 24 days ago \| past
		Can an LLM make a feature-length movie on its own? (lesswrong.com)
		2 points by mchinen 26 days ago \| past
		Recursive Middle Manager Hell (lesswrong.com)
		5 points by rzk 27 days ago \| past
		LLMs are (still) mostly powered by imitative learning, not RL (lesswrong.com)
		1 point by surprisetalk 28 days ago \| past
		Kimi likes causal decision theory more after RL in twin prisoner's dilemmas (lesswrong.com)
		1 point by 0xkato 29 days ago \| past
		More