[croes]

AI doesn’t understand that’s the problem.

If the training data contains some mistakes often it will reproduce them more likely.

Unless there are preprogrammed rules to prevent them.

[nico]

I’ve had really good results, but of course ymmv

As a side note, most good coding models now are also reasoning models, and spend a few seconds “thinking” before giving a reply

That’s by no means infalible, but they’ve come a long way even just in the last 12 months