todsacerdotiMar 6

Hardening Firefox with Anthropic's Red Team

The bugs are the ones that say "using Claude from Anthropic" here: https://www.mozilla.org/en-US/security/advisories/mfsa2026-1...

https://blog.mozilla.org/en/firefox/hardening-firefox-anthro...

https://www.wsj.com/tech/ai/send-us-more-anthropics-claude-s...

https://www.anthropic.com/news/mozilla-firefox-security

Security Vulnerabilities fixed in Firefox 148

Mozilla
Show threadmentalgearMar 6
That's one good use of LLMs: fuzzy testing / attack.
Show threadnzMar 6
Not contradicting this (I am sure it's true), but why is using an LLM for this qualitatively better than using an actual fuzzer?
Show threadsaagarjha
Presumably because people have used actual fuzzers and not found these bugs.
Mar 6 at 1:48pmWeb