[Skywise]

It’s gotten better in the last year I’ve used it but for my coding tasks but it still generates worthless code about 80% of the time.

What it is, is a better search algorithm… but I attribute that to Google et al degrading their search algorithms for ad space. They’ll eventually do the same for AI and we’ll be back to the current state of things.

[Myrddin]

It certainly is better than Google for discovering solutions to edge case problems. The limit is a static training model that is older than the problem you are trying to resolve. I found that with questions about keycloak. I was seeing quirks that were specific to the latest release, but ChatGPT was 5 releases behind.