Discovering Cryptographic Weaknesses with Claude(anthropic.com)

219 points by gslin 2 months ago | 160 comments

Investigating three real-world incidents in our cybersecurity evaluations(anthropic.com)

212 points by surprisetalk 2 months ago | 165 comments

AI models may be capable of self-replicating without access to a datacenter(anthropic.com)

36 points by artninja1988 13 days ago | 26 comments

Anthropic Frontier Red Team post reporting experiments suggesting small AI models may soon self-replicate on commercial IoT devices without datacenter access.

GLM-5.3 and the spread of advanced cyber capabilities(anthropic.com)

157 points by Philpax 26 days ago | 125 comments

Anthropic Frontier Red Team post on GLM-5.3 and how advanced AI cyber-exploit capabilities, first seen in Claude Mythos Preview, are proliferating to other models.

Project Fetch: Phase Two(anthropic.com)

67 points by stopachka 4 months ago | 22 comments

Claude discovers a novel enzyme system with CRISPR-like repeats(anthropic.com)

740 points by raahelb 1 month ago | 740 comments

Anthropic news post announcing that Claude helped discover a novel enzyme system featuring CRISPR-like repeats.

Yes, Claude can do Nine Loops(anthropic.com)

66 points by tzury 1 month ago | 11 comments

Anthropic guest post by physicist Matt von Hippel describing how Claude tackled his challenge on a nine-loop problem from his former subfield of theoretical physics.

Claude Skills are awesome, maybe a bigger deal than MCP(simonwillison.net)

642 points by weinzierl 1 year ago | 332 comments

Simon Willison's blog post about Anthropic's newly introduced Claude Skills, folders of instructions and scripts the model loads when needed, arguing they may matter more than MCP.

Opus 4.5 is not the normal AI agent experience that I have had thus far(burkeholland.github.io)

797 points by tbassetto 9 months ago | 1203 comments

Burke Holland's blog post arguing that Anthropic's Claude Opus 4.5 is a step change in AI coding agent experience.

What makes Claude Code so damn good(minusx.ai)

415 points by samuelstros 1 year ago | 276 comments

A MinusX blog post analyzing what makes Anthropic's Claude Code agent effective, including its system prompts, and how to recreate those design patterns in other agents.

Anthropic officially bans using subscription auth for third party use(code.claude.com)

566 points by theahura 8 months ago | 690 comments

Claude Code documentation page listing legal agreements, compliance certifications, and security information, including terms governing subscription authentication use.

I believe there are entire companies right now under AI psychosis(twitter.com)

2013 points by reasonableklout 5 months ago | 1180 comments

Mitchell Hashimoto's X post arguing some companies are in 'AI psychosis', relying on agents to fix bugs fast (MTTR) at the expense of reliability (MTBF).