Submissions from lesswrong.com

		So You Think You've Awoken ChatGPT (lesswrong.com)
		2 points by surprisetalk 6 hours ago \| past \| 1 comment
		LLMs and Computation Complexity (2023) (lesswrong.com)
		3 points by mathattack 20 hours ago \| past \| 1 comment
		Kolmogorov Complexity [20:48] (lesswrong.com)
		9 points by Bluestein 2 days ago \| past \| discuss
		Gradient Descent on Token Input Embeddings (lesswrong.com)
		3 points by kp1197 3 days ago \| past \| 1 comment
		XAI's Grok 4 has no meaningful safety guardrails (lesswrong.com)
		7 points by mellosouls 5 days ago \| past \| discuss
		Power-seeking, by any person, may be equivalent to minimizing uncertainty (lesswrong.com)
		2 points by OgsyedIE 5 days ago \| past \| discuss
		Field Notes on Shipping with Claude Code (lesswrong.com)
		26 points by ishita159 6 days ago \| past \| 4 comments
		Lessons from the Iraq War for AI Policy (lesswrong.com)
		1 point by ibobev 9 days ago \| past \| discuss
		Some arguments against a land value tax (2024) (lesswrong.com)
		80 points by danny00 10 days ago \| past \| 237 comments
		Spacetime Emerges from Observer-Relative Information (lesswrong.com)
		3 points by vmstabile 11 days ago \| past \| 3 comments
		The Industrial Explosion (lesswrong.com)
		1 point by ibobev 13 days ago \| past \| discuss
		Race and Gender Bias as an Example of Unfaithful Chain of Thought in the Wild (lesswrong.com)
		1 point by supriyo-biswas 14 days ago \| past
		Shutdown Resistance in Reasoning Models (lesswrong.com)
		1 point by ben_w 15 days ago \| past
		A path from autonomy V&V to AGI alignment? (lesswrong.com)
		1 point by yoav_hollander 17 days ago \| past
		Race and Gender Bias as an Example of Unfaithful Chain of Thought in the Wild (lesswrong.com)
		9 points by ibobev 18 days ago \| past
		Dialects for Humans: Sounding Distinct from LLMs (lesswrong.com)
		5 points by nebrelbug 18 days ago \| past \| 1 comment
		Proposal for making credible commitments to AIs (lesswrong.com)
		1 point by surprisetalk 20 days ago \| past
		Machines of Faithful Obedience – LessWrong (lesswrong.com)
		1 point by kiyanwang 20 days ago \| past
		X explains Z% of the variance in Y (lesswrong.com)
		15 points by ibobev 22 days ago \| past \| 1 comment
		X explains Z% of the variance in Y (lesswrong.com)
		4 points by surprisetalk 23 days ago \| past
		A case for courage, when speaking of AI danger (lesswrong.com)
		2 points by ibobev 24 days ago \| past
		The Best of LessWrong (lesswrong.com)
		3 points by sebg 24 days ago \| past
		Situational Awareness: A One-Year Retrospective (lesswrong.com)
		2 points by fofoz 25 days ago \| past
		The V&V method – A step towards safer AGI (lesswrong.com)
		1 point by yoav_hollander 26 days ago \| past
		My Pitch for the AI Village (lesswrong.com)
		1 point by ibobev 26 days ago \| past
		Foom and Doom 1: "Brain in a box in a basement" (lesswrong.com)
		1 point by ibobev 26 days ago \| past
		Metaprogrammatic Hijacking: A New Class of AI Alignment Failure (lesswrong.com)
		1 point by Hiyagann 27 days ago \| past
		Orienting Towards Wizard Power (lesswrong.com)
		1 point by desmondwillow 27 days ago \| past
		A deep critique of AI 2027's bad timeline models (lesswrong.com)
		90 points by paulpauper 28 days ago \| past \| 61 comments
		X explains Z% of the variance in Y (lesswrong.com)
		5 points by kmm 30 days ago \| past
		More