What makes Claude Code so damn good

> "THIS IS IMPORTANT" is still State of the Art

Had a similar problems until I saw the advice "Dont say what it shouldn't but focus on what it should".

i.e. make sure when it reaches for the 'thing', it has the alternative in context.

Haven't had those problems since then.

I mean, if advice like this worked, then why wouldn't Anthropic let the LLM say it, for instance?

Because it’s embarrassing, and probably nobody understands why this works, depending on such heuristics that can completely change in the next model is really bad…

I'd say exactly because behavior might change you have to include proper instructions for each model.

And depending on people in forums to provide these instructions is of course not great.