alt Hacker NewsEven asking it to do little tests, Claude 4.5 Sonnet Thinking still ends up writing tests that do nothing or don't do what it says will do. And it's always fucking cheery about it: "you're code is now production-ready!" and "this is an excellent idea!" and "all errors are now fixed! your code is production-ready!" and "I fixed the compiler issue, we're now production ready!"
...almost as if it's too eager to make its first commit. Much like a junior engineer might be.
It's not eager enough to iterate. Moreover, when it does iterate, it often brings along the same wrong solutions it came up with before.
It's way easier to keep an eye on small changes while iterating with AI than it is with letting it run free in a green field.
Yeah that aggressive sycophancy is incredibly annoying. Someone telling me I'm being a fucking idiot is more useful then "what a fantastic observation! You're so right" for the millionths time.
Even using it to spitball ideas can be a problem. I was using Claude to bounce ideas off of for a problem I was working on it, and it was dead set a specific solution involving a stack and some complex control logic was correct, when it reality it would have made the entire solution far more complicated. All I really needed was a sliding window into an array.