Hardening Firefox with Anthropic's Red Team • Hacker News Board

Re: Hardening Firefox with Anthropic's Red Team

#21

Post by delfinom » Fri, Mar 06, 2026, 1:28 PM UTC

gehsty wrote: post #16

lloydatkinson wrote: post #15

Anthropic feels like they are flailing around constantly trying to find something to do. A C compiler that didn't work, a browser that didn't work, and now solving bugs in Firefox.

This makes sense - they are demonstrating the capability of their core product by doing so? They dont make browsers, c compilers, they sell ai + dev tools.

Capability of a product that makes non-working outputs at a premium?

I can hire an intern for that.

Re: Hardening Firefox with Anthropic's Red Team

#22

Post by robin_reala » Fri, Mar 06, 2026, 1:33 PM UTC

muizelaar wrote: post #7

deafpolygon wrote: post #6

Earlier quoted context omitted.

I’m guessing it might be some of these: https://www.mozilla.org/en-US/security/advisories/mfsa2026-1...

Yeah, the ones reported by Evyatar Ben Asher et al.

I correctly misread that as “et AI”.

Re: Hardening Firefox with Anthropic's Red Team

#23

Post by deafpolygon » Fri, Mar 06, 2026, 1:37 PM UTC

robin_reala wrote: post #22

muizelaar wrote: post #7

Earlier quoted context omitted.

Yeah, the ones reported by Evyatar Ben Asher et al.

I correctly misread that as “et AI”.

“et AI, Brutus!"

Re: Hardening Firefox with Anthropic's Red Team

#24

Post by driverdan » Fri, Mar 06, 2026, 1:40 PM UTC

Anthropic's write up[1] is how all AI companies should discuss their product. No hype, honest about what went well and what didn't. They highlighted areas of improvement too.

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

Re: Hardening Firefox with Anthropic's Red Team

#25

Post by jdiff » Fri, Mar 06, 2026, 1:44 PM UTC

gehsty wrote: post #16

lloydatkinson wrote: post #15

Anthropic feels like they are flailing around constantly trying to find something to do. A C compiler that didn't work, a browser that didn't work, and now solving bugs in Firefox.

This makes sense - they are demonstrating the capability of their core product by doing so? They dont make browsers, c compilers, they sell ai + dev tools.

Seems like a poor advertisement for their product if their shining example of utility is a broken compiler that doesn't function as the README indicates.

Re: Hardening Firefox with Anthropic's Red Team

#26

Post by nz » Fri, Mar 06, 2026, 1:45 PM UTC

mentalgear wrote: post #3

That's one good use of LLMs: fuzzy testing / attack.

Not contradicting this (I am sure it's true), but why is using an LLM for this qualitatively better than using an actual fuzzer?

Re: Hardening Firefox with Anthropic's Red Team

#27

Post by saagarjha » Fri, Mar 06, 2026, 1:48 PM UTC

lloydatkinson wrote: post #15

Anthropic feels like they are flailing around constantly trying to find something to do. A C compiler that didn't work, a browser that didn't work, and now solving bugs in Firefox.

Solving bugs in Firefox is quite impressive.

Re: Hardening Firefox with Anthropic's Red Team

#28

Post by saagarjha » Fri, Mar 06, 2026, 1:48 PM UTC

nz wrote: post #26

mentalgear wrote: post #3

That's one good use of LLMs: fuzzy testing / attack.

Not contradicting this (I am sure it's true), but why is using an LLM for this qualitatively better than using an actual fuzzer?

Presumably because people have used actual fuzzers and not found these bugs.

Re: Hardening Firefox with Anthropic's Red Team

#29

Post by larodi » Fri, Mar 06, 2026, 1:49 PM UTC

fcpk wrote: post #2

The fact there is no mention of what were the bugs is a little odd. It'd really be nice to see if this is a "weird never happening edge case" or actual issues. LLMs have uncanny abilities to identify failure patterns that it has seen before, but they are not necessarily meaningful.

The fact that some of the Claude-discovered bugs were quite severe is also a little more than something to brush off as "yeah, LLM, whatever". The lists reads quite meaningful to me, but I'm not a security expert anyways.

Re: Hardening Firefox with Anthropic's Red Team

#30

Post by g947o » Fri, Mar 06, 2026, 1:49 PM UTC

> Firefox was not selected at random. It was chosen because it is a widely deployed and deeply scrutinized open source project — an ideal proving ground for a new class of defensive tools.

What I was thinking was, "Chromium team is definitely not going to collaborate with us because they have Gemini, while Safari belongs to a company that operates in a notoriously secretive way when it comes to product development."