Submissions from anthropic.com

		The assistant axis: situating and stabilizing the character of LLMs (anthropic.com)
		127 points by mfiguiere 22 days ago \| past \| 26 comments
		Anthropic Economic Index Report (anthropic.com)
		2 points by vinhnx 22 days ago \| past
		Anthropic Economic Index Economic Primitives (anthropic.com)
		1 point by gmays 23 days ago \| past
		Demystifying Evals for AI Agents (anthropic.com)
		2 points by handfuloflight 24 days ago \| past
		How scientists are using Claude to accelerate research and discovery (anthropic.com)
		124 points by gmays 24 days ago \| past \| 75 comments
		Demystifying Evals for AI Agents (anthropic.com)
		2 points by theptip 25 days ago \| past
		Anthropic Economic Index economic primitives (anthropic.com)
		3 points by atlasunshrugged 26 days ago \| past
		Finding bugs across the Python ecosystem with Claude and property-based testing (anthropic.com)
		1 point by mmaaz 27 days ago \| past
		Anthropic Labs (anthropic.com)
		2 points by kerim-ca 27 days ago \| past
		Advancing Claude in healthcare and the life sciences (anthropic.com)
		32 points by ta_u 30 days ago \| past \| 2 comments
		Demystifying Evals for AI Agents (anthropic.com)
		3 points by dvorka 30 days ago \| past
		Advancing Claude in healthcare and the life sciences (anthropic.com)
		1 point by meetpateltech 30 days ago \| past \| 1 comment
		Anthropic: Demystifying Evals for AI Agents (anthropic.com)
		4 points by Bayram 31 days ago \| past \| 1 comment
		Writing Evals for AI agents (anthropic.com)
		3 points by seshagiric 31 days ago \| past
		More efficient protection against universal jailbreaks (anthropic.com)
		2 points by pretext 32 days ago \| past \| 1 comment
		Demystifying Evals for AI Agents (anthropic.com)
		2 points by vinhnx 32 days ago \| past \| 1 comment
		Constitutional Classifiers++: More efficient protection against jailbreaks (anthropic.com)
		3 points by Tiberium 32 days ago \| past
		Demystifying Evals for AI Agents (anthropic.com)
		5 points by pretext 32 days ago \| past \| 1 comment
		Experimenting with AI to defend critical infrastructure (anthropic.com)
		3 points by Kristopher1337 33 days ago \| past \| 1 comment
		Bloom: An open source tool for automated behavioral evaluations (anthropic.com)
		2 points by pbd 38 days ago \| past
		Bloom: an open source tool for automated behavioral evaluations (anthropic.com)
		3 points by maluta 50 days ago \| past
		Bloom: An open source tool for automated behavioral evaluations (anthropic.com)
		2 points by sonabinu 50 days ago \| past
		Bloom: an open source tool for automated behavioral evaluations (anthropic.com)
		1 point by gangtao 50 days ago \| past
		Project Vend: Phase Two (anthropic.com)
		197 points by kubami 50 days ago \| past \| 92 comments
		Bloom: an open source tool for automated behavioral evaluations (anthropic.com)
		1 point by gmays 51 days ago \| past
		Bloom: an open source tool for automated behavioral evaluations (anthropic.com)
		4 points by Garbage 52 days ago \| past
		Training and Evaluating LLMs as General-Purpose Activation Explainers (anthropic.com)
		1 point by not4uffin 53 days ago \| past
		Project Vend: Phase Two (anthropic.com)
		1 point by Anon84 54 days ago \| past
		Protecting the well-being of our users (anthropic.com)
		2 points by amrrs 54 days ago \| past
		Project Vend: Phase Two (anthropic.com)
		2 points by dcre 54 days ago \| past \| 1 comment
		More