Anthropic’s team got in touch with Firefox engineers after using Claude to identify security bugs in our JavaScript engine. Critically, their bug reports included minimal test cases that allowed our security team to quickly verify and reproduce each issue.

no comments (yet)

sorted by: hot top controversial new old
there doesn't seem to be anything here
9 comments in c/technology@lemmy.world view that post
[–] 29 points 8 months ago (7 children)

I'll take a more secure Firefox. If this is how it is achieved, so be it.

  • source
  • hideshow 7 child comments
  • [–] 10 points 8 months ago (6 children)

    Yeah I'm actually kinda into this. Even if the AI vomits up a bunch of hallucinated vulnerabilities, there's a team of (presumably) capable people there to figure that out. Seems like a pretty valid use for the technology.

  • source
  • parent
  • hideshow 6 child comments
  • [–] -3 points 8 months ago (5 children)

    Hallucinated? From researched and documented code spelunking?

  • source
  • parent
  • hideshow 5 child comments
  • [–] 2 points 8 months ago (4 children)

    That's...exactly my point though...

  • source
  • parent
  • hideshow 4 child comments
  • [–] -1 points 8 months ago (3 children)
  • [–] 3 points 8 months ago (2 children)

    That even though the team is using AI to check for vulnerabilities, they're trained and know when their AI is hallucinating and when it's not.

  • source
  • parent
  • hideshow 2 child comments
  • [–] -1 points 8 months ago (1 child)

    I guess I’m not sure how hallucinating and reading from source code are overlapping. Do you think these models are just barfing back garbage nonsense?

  • source
  • parent
  • hideshow 1 child comment
  • [–] 12 points 8 months ago
    1 comment in c/firefox@lemmy.ml view that post
    [+] -15 points 8 months ago (1 child)
  • 1 comment in c/auai@programming.dev view that post
    [–] 6 points 8 months ago

    Finally, something useful.
    Now let's hope they don't make the AI "patch" it.

  • source