Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I have a hard time believing that Claude instantly figured out this was malware...

I've fed it obfuscated JavaScript before, and it couldn't figure it out... and then there was the time I tried to teach it nftables... whooo boy...

 help



If you read the transcript it repeatedly made the incorrect assertion (hallucinated) that it’s totally normal for Claude Code to use Base64 armoring.

It’s not surprising it can “read” Base64 though; such was demonstrated back in GPT-3 days. Nontrivial obfuscation might not be one-shotted, but Claude has access to a code interpreter and can certainly extract and step through the decoder routine itself as a malware analyst would.

nftables is a different problem though. It’s apparent that if something isn’t well understood—i.e, there are tons of badly-formed examples on StackExchange—LLMs will fail to learn it too. I’ve seen this with things as “simple” as Bash string interpolation rules like ${var:+blah}. More often than not I’m humbled when I think I’ll learn it better and then find myself swearing at poorly-written documentation and patently false Q&A advice.


I think the usual response to that is "have you tried again recently?"

3 weeks ago?

They are really good at this, had codex discover similar malware from another supply chain attack months ago because my laptop was running hot. Actually crazy times we live in, I would certainly not be able to discover this without agent help.

> and then there was the time I tried to teach it nftables

I think this deserves a short story!


My home router is apparently special because I want a private dmz and inbound blocklists... firewalld couldn't do what I wanted, so I tried nftables, and that went down a rabbit hole that made me wish iptables and ipset weren't being replaced.

Except in this case the code wasn't obfuscated, right?

Hard to know with this nondeterministic shit.



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: