[CaptainOfCoit]

To be fair, most of the times, the tools works best with the models trained with those tools in mind, and vice-versa.

Not to mention not all models/inference works the same way so you can't really replicate the same experience. For example, new Harmony format means you can now inject messages while GPT-OSS is running inference, but obviously Claude Code don't support that because their models don't support that.

[kaycey2022]

>most of the times, the tools works best with the models trained with those tools in mind

This is a garbage state of affairs though

[CaptainOfCoit]

What do you expect? People building software using other models than they themselves develop? Or people training the models train them for software that isn't the software they develop themselves?

It's like saying official car repair shops should repair any type of car, not just their brand. That's just not how the real world works.

[OJFord]

Or they just don't even do it? Michelin tyres aren't best fitted by a Michelin shop, those don't exist. You go to KwikFit or whatever you think's best, and get Michelin or Continental or Pirelli or whatever you think's best fitted.

[antonvs]

Terrible analogy, because the issues involved in fitting car tires of different brands are in no way comparable to the differences between LLM behavior across models.