HN2new | past | comments | ask | show | jobs | submit | fromlogin
Writing Evals for AI agents (anthropic.com)
3 points by seshagiric 23 days ago | past
More efficient protection against universal jailbreaks (anthropic.com)
2 points by pretext 24 days ago | past | 1 comment
Demystifying Evals for AI Agents (anthropic.com)
2 points by vinhnx 24 days ago | past | 1 comment
Constitutional Classifiers++: More efficient protection against jailbreaks (anthropic.com)
3 points by Tiberium 24 days ago | past
Demystifying Evals for AI Agents (anthropic.com)
5 points by pretext 24 days ago | past | 1 comment
Experimenting with AI to defend critical infrastructure (anthropic.com)
3 points by Kristopher1337 25 days ago | past | 1 comment
Bloom: An open source tool for automated behavioral evaluations (anthropic.com)
2 points by pbd 30 days ago | past
Bloom: an open source tool for automated behavioral evaluations (anthropic.com)
3 points by maluta 41 days ago | past
Bloom: An open source tool for automated behavioral evaluations (anthropic.com)
2 points by sonabinu 42 days ago | past
Bloom: an open source tool for automated behavioral evaluations (anthropic.com)
1 point by gangtao 42 days ago | past
Project Vend: Phase Two (anthropic.com)
197 points by kubami 42 days ago | past | 92 comments
Bloom: an open source tool for automated behavioral evaluations (anthropic.com)
1 point by gmays 43 days ago | past
Bloom: an open source tool for automated behavioral evaluations (anthropic.com)
4 points by Garbage 44 days ago | past
Training and Evaluating LLMs as General-Purpose Activation Explainers (anthropic.com)
1 point by not4uffin 45 days ago | past
Project Vend: Phase Two (anthropic.com)
1 point by Anon84 45 days ago | past
Protecting the well-being of our users (anthropic.com)
2 points by amrrs 46 days ago | past
Project Vend: Phase Two (anthropic.com)
2 points by dcre 46 days ago | past | 1 comment
Natural Emergent Misalignment from Reward Hacking in Production RL [pdf] (anthropic.com)
1 point by samlinnfer 51 days ago | past
Donating the Model Context Protocol and establishing the Agentic AI Foundation (anthropic.com)
288 points by meetpateltech 55 days ago | past | 145 comments
Anthropic Interviewer (anthropic.com)
1 point by erhuve 57 days ago | past
Anthropic Interviewer (anthropic.com)
2 points by ta_u 59 days ago | past
Anthropic Interviewer (anthropic.com)
1 point by victorbuilds 59 days ago | past
Anthropic Interviewer: What 1,250 professionals told us about working with AI (anthropic.com)
2 points by miltava 60 days ago | past | 1 comment
Anthropic Interviewer: What 1,250 professionals told us about working with AI (anthropic.com)
6 points by meetpateltech 60 days ago | past
How AI is transforming work at Anthropic (anthropic.com)
9 points by achow 61 days ago | past | 3 comments
Claude for Nonprofits \ Anthropic (anthropic.com)
1 point by raybb 61 days ago | past | 1 comment
How AI is transforming work at Anthropic (anthropic.com)
4 points by mybestday 61 days ago | past
How AI is transforming work at Anthropic (anthropic.com)
26 points by mfiguiere 62 days ago | past | 12 comments
Anthropic Acquires Bun (anthropic.com)
99 points by httpteapot 62 days ago | past | 15 comments
AI agents find $4.6M in blockchain smart contract exploits (anthropic.com)
215 points by bpierre 63 days ago | past | 121 comments

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: