[rgovostes]

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.