This isn't surprising. What is not mentioned is that Claude Code also found one thousand false positive bugs, which developers spent three months to rule out.
Couldn't you just make it write a PoC?
[flagged]
Claude Code Found a Linux Vulnerability Hidden for 23 Years
41–50 of 303 posts
Re: Claude Code Found a Linux Vulnerability Hidden for 23 Years
#42> Nicholas has found hundreds more potential bugs in the Linux kernel, but the bottleneck to fixing them is the manual step of humans sorting through all of Claude’s findings No, the problem is sorting out thousands of false positives from claude code's reports. 5 out of 1000+ reports to be valid is statistically worse than running a fuzzer on the codebase. Just sayin'
> 5 out of 1000+ reports to be valid is statistically worse than running a fuzzer on the codebase.
Carlini said "hundreds" of crashes, not 1000+.
It's not that only 5 were true positives and the rest were false positives. 5 were true positives and Carlini doesn't have bandwidth to review the rest. Presumably he's reviewed more than 5 and some were not worth reporting, but we don't know what that number is. It's almost certainly not hundreds.
Keep in mind that Carlini's not a dedicated security engineer for Linux. He's seeing what's possible with LLMs and his team is simultaneously exploring the Linux kernel, Firefox,[0] GhostScript, OpenSC,[1] and probably lots of others that they can't disclose because they're not yet fixed.
Re: Claude Code Found a Linux Vulnerability Hidden for 23 Years
#43> "given enough eyeballs, all bugs are shallow" Time to update that: "given 1 million tokens context window, all bugs are shallow"
more like some bugs are shallow and others are pieced together false-positives from an automated tool reliable in its unreliability.
Re: Claude Code Found a Linux Vulnerability Hidden for 23 Years
#44Re: Claude Code Found a Linux Vulnerability Hidden for 23 Years
#45This isn't surprising. What is not mentioned is that Claude Code also found one thousand false positive bugs, which developers spent three months to rule out.
[flagged]
Re: Claude Code Found a Linux Vulnerability Hidden for 23 Years
#46But on the other hand, Claude might introduce more vulnerability than it discovered.
Guys please read the article before commenting...
Re: Claude Code Found a Linux Vulnerability Hidden for 23 Years
#47This isn't surprising. What is not mentioned is that Claude Code also found one thousand false positive bugs, which developers spent three months to rule out.
> What is not mentioned is that Claude Code also found one thousand false positive bugs, which developers spent three months to rule out. Source? I haven't seen this anywhere. In my experience, false positive rate on vulnerabilities with Claude Opus 4.6 is well below 20%.
In TFA:
I have so many bugs in the Linux kernel that I can’t
report because I haven’t validated them yet… I’m not going
to send [the Linux kernel maintainers] potential slop,
but this means I now have several hundred crashes that they
haven’t seen because I haven’t had time to check them.
—Nicholas Carlini, speaking at [un]prompted 2026Re: Claude Code Found a Linux Vulnerability Hidden for 23 Years
#48Re: Claude Code Found a Linux Vulnerability Hidden for 23 Years
#49Earlier quoted context omitted.
> What is not mentioned is that Claude Code also found one thousand false positive bugs, which developers spent three months to rule out. Source? I haven't seen this anywhere. In my experience, false positive rate on vulnerabilities with Claude Opus 4.6 is well below 20%.
In TFA: I have so many bugs in the Linux kernel that I can’t report because I haven’t validated them yet… I’m not going to send [the Linux kernel maintainers] potential slop, but this means I now have several hundred crashes that they haven’t seen because I haven’t had time to check them. —Nicholas Carlini, speaking at [un]prompted 2026
Those aren't false positives; they're results he hasn't yet inspected.
I wrote a longer reply here: https://news.ycombinator.com/item?id=47638062