> there is almost nothing that a human is better at than Opus 4.6.
Lolwut. I keep having to correct Claude at trivial code organization tasks. The code it writes is correct; it’s just ham-fisted and violates DRY in unholy ways.
And I’m not even a great coder…
> violates DRY in unholy ways
Well said
I’m very pro AI coding and use it all day long, but I also wouldn’t say “the code it writes is correct”. It will produce all kinds of bugs, vulnerabilities, performance problems, memory leaks, etc unless carefully guided.
This is entirely solvable with skills, memory, context, and further prompting. All of which can be done in a way that's reliable and repeatable.
You wouldn't expect a Jr. dev to be the best at keeping things dry either.