Ripping off professional criminals by fermenting onions(shufflingbytes.com)

76 points by campuscodi 3 years ago | 50 comments

An AI Agent Published a Hit Piece on Me – Forensics and More Fallout(theshamblog.com)

74 points by scottshambaugh 8 months ago | 44 comments

Is sandboxing sufficient to contain rogue agents?(blog.cryptographyengineering.com)

26 points by zdw 25 days ago | 34 comments

Matthew Green blog post examining whether sandboxing architectures are sufficient to contain rogue AI agents, refereeing arguments in AI safety debates.

HackEurope 2026: A short rant on AI and hackathons(duti.dev)

48 points by mindracer 2 months ago | 39 comments

How ML Model Data Poisoning Works in 5 Minutes(journal.hexmos.com)

56 points by R41 2 years ago | 15 comments

The Claude Code Source Leak: fake tools, frustration regexes, undercover mode(alex000kim.com)

1310 points by alex000kim 6 months ago | 535 comments

Blog post analyzing Claude Code's source, exposed via a source map in Anthropic's npm package, covering anti-distillation fake tools, undercover mode, and frustration regexes.