Submissions from lesswrong.com

		How My Students Think About AI (lesswrong.com)
		35 points by paulpauper 6 hours ago \| past \| 6 comments
		Adaptive Agentic Worms Are Here (lesswrong.com)
		2 points by speckx 1 day ago \| past \| discuss
		Astra and Fable still hack on simple variants of alignment evals from 2025 (lesswrong.com)
		1 point by yurivish 2 days ago \| past \| discuss
		Interpreting GPT: The Logit Lens (lesswrong.com)
		1 point by Bluestein 2 days ago \| past \| discuss
		From safety research prompt to cross-model universal jailbreak (lesswrong.com)
		2 points by gmays 3 days ago \| past \| discuss
		My Students Think About AI (lesswrong.com)
		4 points by alphabetatango 6 days ago \| past \| 1 comment
		Asking agents to make money to survive (lesswrong.com)
		3 points by paraschopra 6 days ago \| past \| discuss
		What is nueralese and why is it bad (lesswrong.com)
		77 points by tristanMatthias 7 days ago \| past \| 59 comments
		How concerned should we be about Astra's recurrent architecture? (lesswrong.com)
		151 points by yurivish 7 days ago \| past \| 129 comments
		METR Researcher Thomas Kwa Hired by OpenAI (lesswrong.com)
		1 point by qlte 8 days ago \| past \| discuss
		The Library of Scott Alexandria (lesswrong.com)
		4 points by benatkin 8 days ago \| past \| 1 comment
		Models may behave differently in graded episode (lesswrong.com)
		2 points by ddp26 8 days ago \| past \| discuss
		AGI and the Efficient Market Hypothesis (2023) (lesswrong.com)
		2 points by Metacelsus 9 days ago \| past \| 1 comment
		How My Students Think About AI (lesswrong.com)
		5 points by pella 10 days ago \| past \| 1 comment
		P(Kill-Switch\|Detection) (lesswrong.com)
		2 points by kp1197 10 days ago \| past \| discuss
		Starting AI Safety Study Group to Do Arena Curriculum (lesswrong.com)
		2 points by joozio 11 days ago \| past \| discuss
		Cooperating with aliens and AGIs: An ECL explainer (lesswrong.com)
		3 points by Bluestein 15 days ago \| past
		Prompt Sufficiency: A Missive for the Managerial Class (lesswrong.com)
		1 point by kp1197 18 days ago \| past
		We Must Remember That Our World Contains Hell (lesswrong.com)
		1 point by paulpauper 20 days ago \| past
		LLMs are (still) mostly powered by imitative learning, not RL (lesswrong.com)
		3 points by wslh 20 days ago \| past
		Can an LLM make a feature-length movie on its own? (lesswrong.com)
		2 points by mchinen 22 days ago \| past
		Recursive Middle Manager Hell (lesswrong.com)
		5 points by rzk 23 days ago \| past
		LLMs are (still) mostly powered by imitative learning, not RL (lesswrong.com)
		1 point by surprisetalk 24 days ago \| past
		Kimi likes causal decision theory more after RL in twin prisoner's dilemmas (lesswrong.com)
		1 point by 0xkato 25 days ago \| past
		You're Absolutely Right (lesswrong.com)
		5 points by LinchZhang 29 days ago \| past \| 1 comment
		Misaligned AIs could use killer robots to take over (lesswrong.com)
		7 points by x312 30 days ago \| past \| 4 comments
		Don't Build Mindreading (lesswrong.com)
		21 points by paulpauper 31 days ago \| past \| 14 comments
		How to be an AI safety research engineer (lesswrong.com)
		1 point by joozio 32 days ago \| past
		What I did in the hedonium shockwave, by Emma, age six and a half (lesswrong.com)
		12 points by paulpauper 32 days ago \| past \| 2 comments
		Inducing self-other overlap with SFT reduces deception at scale, but generaliza (lesswrong.com)
		1 point by joozio 33 days ago \| past
		More