Constitutional Classifiers: Defending against universal jailbreaks (anthropic.com) | HN Screenshots

YHacker Newsscreenshots

Screenshot of anthropic.com: Constitutional Classifiers: Defending against universal jailbreaks

First screen, captured 1 year ago.

Looks similar

Screenshot of anthropic.com: Anthropic: Expanding Access to Claude for Government

Anthropic: Expanding Access to Claude for Government (anthropic.com)

92 points by Luuucas 2 years ago | 41 comments

Screenshot of anthropic.com: Clio: A system for privacy-preserving insights into real-world AI use

Clio: A system for privacy-preserving insights into real-world AI use (anthropic.com)

113 points by simonw 1 year ago | 38 comments

Screenshot of anthropic-timeline.vercel.app: Timeline: Anthropic, OpenAI, and U.S. Government

Timeline: Anthropic, OpenAI, and U.S. Government (anthropic-timeline.vercel.app)

27 points by vldszn 8 months ago | 5 comments

Screenshot of anthropic.com: Using Claude to reduce the attack surface of code

Using Claude to reduce the attack surface of code (anthropic.com)

104 points by dnw 5 days ago | 91 comments

Anthropic Frontier Red Team post on research into using Claude to reduce the attack surface of code for cyber defense.

attack-surface-reduction claude anthropic vulnerability-research

Screenshot of bbc.com: Anthropic blocks 'malicious use' of AI that could develop biological weapons

Anthropic blocks 'malicious use' of AI that could develop biological weapons (bbc.com)

6 points by mgh2 1 month ago | 2 comments

Screenshot of anthropic.com: Agentic Misalignment: How LLMs could be insider threats

Agentic Misalignment: How LLMs could be insider threats (anthropic.com)

70 points by helloplanets 1 year ago | 64 comments