|
|
|
|
|
|
by hypfer
23 hours ago
|
|
|
Opus in my experience is equally unpleasant "character"-wise, but at least it actually gets stuff done more often, so it's at least slightly more earned at that.
It's still a neurotic cargo-culting dogmatic idiot, but one that at least sometimes does produce deliverables instead of only bottom-tier HN-esque opinions. Hmm. I think I might just fundamentally disagree with Anthropic about the idea of what a "tool" should be. |
|
|
> But re-reading the comment:
> "In the real world however, it does not. Hence, in the future we might fail this check even if it works within this limited check."
> The comment says "we might fail this check even if it works" — implying the original intent was to always fail (return 1) as a conservative stance, leaving room to tighten it later. The new code does the opposite of what the comment describes.
> So either:
> 1) The comment needs updating to reflect the new intent, or
> 2) The logic is wrong and should still return 1 unconditionally if the original intent was preserved.
> Which is it — did you intentionally want to succeed when X works, making the comment outdated? Or should the return 1 be restored?
> User: did you see the "in the future"?
> Yes, fair point — "in the future we might fail this check" is forward-looking, not a statement of current intent. The comment is saying the door is left open to tightening the check later, not that it should currently always fail. So the current code is correct and the comment still holds. All good.
___
It reads/comprehends 5% of what is on screen but acts like it knows it all, bossing you around. Why is it like this. What's wrong with Anthropic and what's wrong with people _not_ getting incredibly angry at that unearned smartass.