logoalt Hacker News

argee • yesterday at 7:35 PM • 2 replies • view on HN

That's right. And you have to read what the agent is doing as well. Once I said (Opus 5.5), given this list, find issues that are both critical and related to {X feature}.

Guess what: because I said "both", Opus decided I was looking to pick out exactly two of the issues. If I hadn't read that reasoning log, I would've remained oblivious and thought there were only two it could find.


Replies

nhecker • yesterday at 11:55 PM

You get a reasoning trace from Opus 5.5?

➕ show 1 reply
epihelix • yesterday at 10:41 PM

To be fair, that's a pebkac problem. You got exactly what you requested (and the language was unambiguous).

This is like writing `if (cond_x && cond_y) {}` and then blaming the compiler because it didn't realise that actually meant to write `if (cond_x || cond_y) {}`.

➕ show 2 replies