Local Qwen isn't a worse Opus, it's a different tool

Re:Local Qwen isn't a worse Opus, it's a different tool by madeofpalk on Thursday June 18, 2026 @05:52AM (#48583106)

Except, where every different model and version is like a different person where you need to learn their idiosyncrasies of how they work every other month.

It's a very very bizarre way to use a computer.

Personally, I just don't. I'll use and prompt the LLMs the way that feels natural to me and move on with my life. Maybe I don't always get completely optimal results from them, but im also not spending half my day pleading with the computer to do a task.

[ Parent | on HN ]

Re:Local Qwen isn't a worse Opus, it's a different tool by user43928 on Thursday June 18, 2026 @08:15AM (#48584172)

I also don't think I need to prompt Claude differently than Codex.

The most important thing to be aware of in my opinion would be that Claude is better at UI design, and leaves a lot more comments in the code.

Other than that the results seem similar, at least functionally. I do not usually review the code style.

[ Parent | on HN ]