HN

Comments (199)

• Menu

  mattbee
  Pasting a big batch of new code and asking Claude "what have I forgotten? Where are the bugs?" is a very persuasive on-ramp for developers new to AI. It spots threading & distributed system bugs that would have taken hours to uncover before, and where there isn't any other easy tooling.I bet there's loads of cryptocurrency implementations being pored over right now - actual money on the table.
• Menu

  userbinator
  Not "hidden", but probably more like "no one bothered to look".declares a 1024-byte owner ID, which is an unusually long but legal value for the owner ID.When I'm designing protocols or writing code with variable-length elements, "what is the valid range of lengths?" is always at the front of my mind.it uses a memory buffer that’s only 112 bytes. The denial message includes the owner ID, which can be up to 1024 bytes, bringing the total size of the message to 1056 bytes. The kernel writes 1056 bytes into a 112-byte bufferThis is something a lot of static analysers can easily find. Of course asking an LLM to "inspect all fixed-size buffers" may give you a bunch of hallucinations too, but could be a good starting point for further inspection.
• fguerraz
  Interestingly, I think 3 or 4 out of the 5 bugs would have been prevented / mitigated quite well using https://github.com/anthraxx/linux-hardened patches...(disabled io_uring, would have crashed the kernel on UAF, and made exploitation of the heap overflow very unreliable)
• PeterStuer
  Those 3 letter agencies are going to see their stash of 0-days dwindle so hard.
• DGAP
  I replicated this experiment on several production codebases and got several crits. Lots of dupes, lots of false positives, lots of bugs that weren't actually exploitable, lots of accepted/ known risks. But also, crits!
• summarity
  Related work from our security lab:Stream of vulnerabilities discovered using security agents (23 so far this year): https://securitylab.github.com/ai-agents/Taskflow harness to run (on your own terms): https://github.blog/security/how-to-scan-for-vulnerabilities...
• e12e
  I wonder about the "video running in the background" during qna of the talk:https://youtu.be/1sd26pWhfmg?is=XLJX9gg0Zm1BKl_5Did he write an exploit for the NFS bug that runs via network over USB? Seems to be plugging in a SoC over USB...?
• Menu

  yunnpp
  I really "like" the premise of this talk: "We are releasing dangerous weapons, help us make the world safer! Also, it'll cost you a subscription, and we'll profit from it." Imagine if the speaker was a biochemist talking about releasing chemical bombs in your neighborhood that somehow you just could not avoid. The software industry is such a joke right now.
• misiek08
  Do not expect so many more reports. Expect so many more attacks ;)
• Menu

  dist-epoch
  > "given enough eyeballs, all bugs are shallow"Time to update that:"given 1 million tokens context window, all bugs are shallow"
• Menu

  cesaref
  I'm interested in the implications for the open source movement, specifically about security concerns. Anyone know is there has been a study about how well Claude Code works on closed source (but decompiled) source?
• Menu

  jazz9k
  This does sound great, but the cost of tokens will prevent most companies from using agents to secure their code.
• Menu

  eichin
  An explanation of the Claude Opus 4.6 linux kernel security findings as presented by Nicholas Carlini at unpromptedcon.
• rixrax
  I hope next up is the performance and bloat that the LLMs can try and improve.Especially on perf side I would wager LLMs can go from meat sacks what ever works to how do I solve this with best available algorithm and architecture (that also follows some best practises).
• Menu

  skeeter2020
  And with AI generating vulnerabilities at an accelerated pace this business is only getting bigger. Welcome to the new antivirus!
• alsanan2
  making public that AI is able of founding that kind of vulnerabilities is a big problem. In this case it's nice that the vulnerability has been closed before publishing but in case a cracker founds it, the result would be extremately different. This kind of news only open eyes for the crackers.
• Menu

  up2isomorphism
  But on the other hand, Claude might introduce more vulnerability than it discovered.
• jeremie_strand
  [dead]
• jeremie_strand
  [dead]
• Menu

  jason1cho
  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.
• adamsilvacons
  [dead]
• dfir-lab
  [dead]
• LeonTing1010
  [dead]
• claudexai
  [dead]
• pithtkn
  [dead]
• roach54023
  [dead]
• Menu

  lnkl
  [flagged]
• Menu

  cookiengineer
  > 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 findingsNo, 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'
• Menu

  desireco42
  A developer using Claude Code found this bug. Claude is a tool. It is used by developers. It should not sign commits. Neovim never tried to sign commits with me, nor Zed.
• Menu

  _pdp_
  The title is a little misleading.It was Opus 4.6 (the model). You could discover this with some other coding agent harness.The other thing that bugs me and frankly I don't have the time to try it out myself, is that they did not compare to see if the same bug would have been found with GPT 5.4 or perhaps even an open source model.Without that, and for the reasons I posted above, while I am sure this is not the intention, the post reads like an ad for claude code.
• skyskys
  no hecking wayyy!!!! claude chud code!!!