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.

So it's even more human than we thought

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.

> there is almost nothing that a human is better at than Opus 4.6.

> You wouldn't expect a Jr. dev to be the best at keeping things dry either.

So a junior dev is better than almost all humans at everything?

Yea the “you’re holding it wrong” argument. Never takes long to pop up.

> You wouldn't expect a Jr. dev to be the best at keeping things dry either.

Did you read the comment I replied to? The premise was

> there is almost nothing that a human is better at than Opus 4.6.

So which is it? Is Claude the junior dev “better at” most things than a human or not? Sorry, you can’t play your argument both ways.

> violates DRY in unholy ways

Well said