This is accurate.

It’s also why I don’t trust the hype around having AI write tests. The tests should be the spec the AI uses to write the production code and a human should write the tests.

A prompt is not a test or a spec.
Reposted from hailey
i think its pretty cool. i think its awesome to watch the system figure out how to fix problems (though, i'd be scared to death of how it tries to fix problems in bigger codebases). but this isn't anywhere near being affordable enough or trustworthy enough to use for anything serious

Comments