... or one person has a very strong mental model of what he expects to do, but the LLM has other ideas. FWIW I'm very happy with CC and Opus, but I don't treat it as a subordinate but as a peer; I leave it enough room to express what it thinks is best and guide later as needed. This may not work for all cases.

▲

sarchertech 2 hours ago | parent [-]

If you don’t have a very strong mental model for what you are working on Claude can very easily guide in you into building the wrong thing.

For example I’m working on a huge data migration right now. The data has to be migrated correctly. If there are any issues I want to fail fast and loud.

Claude hates that philosophy. No matter how many different ways I add my reasons and instructions to stop it to the context, it will constantly push me towards removing crashes and replacing them with “graceful error handling”.

If I didn’t have a strong idea about what I wanted, I would have let it talk me into building the wrong thing.

Claude has no taste and its opinions are mostly those of the most prolific bloggers. Treating Claude like a peer is a terrible idea unless you are very inexperienced. And even then I don’t know if that’s a good idea.

	▲	oops an hour ago \| parent [-]
		That’s interesting to hear as for me Claude has been quite good about writing code that fails fast and loud and has specifically called it out more than once. It has also called out code that does not fail early in reviews.