> chatgpt-4o-latest, but it's bad because they continuously update it

Version explicitly marked as "latest" being continuously updated it? Crazy.

No one's arguing that it's improperly labelled, but if you're going to use it via API, you might want consistency over bleeding edge.

Lots of the other models are checkpoint releases, and latest is a pointer to the latest checkpoint. Something being continuously updated is quite different and worth knowing about.

It can be both properly communicated and still bad for API use cases.