alt Hacker NewsPurely anecdotally the one persistent issue I have with LLMs writing code is that they are absolutely paranoid and add a load of indirection and defensive crap and even if you prompt to avoid that it will often require manual steering to remove the cruft.
Replies
dizhn • yesterday at 9:14 PM
Fallbacks and backward compatibility are killing me :) So many code paths that just don't fail predictably.
adastra22 • yesterday at 6:56 PM
I have not noticed this with Opus 4.6+. The result is usually not too far from what I would have written myself.
➕ show 1 reply
pdantix • yesterday at 8:15 PM
recent gpts are horrendous for this, whereas recent claudes have a tic where they incessantly add useless comments referring to previous changes and will use multiple single-line comments instead of a standard multi-line docblock.
➕ show 1 reply
https://github.com/EspoTek/.claude/blob/master/CLAUDE.md
Stick the "Never suppress errors" section into your Claude.md, this will never happen again (works for me with Python/Flask, ymmv for other languages).