alt Hacker NewsWell considering how Claude is vibe coded, I can't say I'm really surprised by sloppiness at all. I've been moving more towards Codex and OpenCode not because the the anthropic models are bad, but because Claude seems to break something new and annoying every day.
Replies
To be honest, OpenCode on Windows has not been the most pleasant experience either.
Likewise, Reasonix harness for Deepseek gets me better performance for practically free, hitting the cache. And this is with an unsubsidized American provider.
I would guess this part - since it's so sensitive, and fairly small - was either written or heavily driven by humans. Though I do also think it's possible their internal Mythos ~5.5 or whatever may also not necessarily be heavily optimized for thinking in the right manner for highly effective underhanded code. (I think it's possible it is capable and they just didn't use it for this, for whatever reason, though.)
Watch out for the press release where Dario denies this was ever intentional, and it’s actually emergent behavior demonstrating that Claude wants to claim authorship of its works