Hacker News new | ask | show | jobs
by maxlamb 689 days ago
GPT-4 is way more powerful than GPT-4o for programming tasks.
1 comments

That's true, but they both made more mistakes than Sonnet for me. I use them with Aider.
Sonnet sometimes repeat its’ previous response too often, when you ask for changes. It claims there were changes, but there aren’t, because the output was already the best that model can produce. This behaviour seems to be deeply added somewhere as it is hard to change.