[samuelknight]

It's not a smell. Why should these developers rebuild a core piece of their stack every few months. Switching out a model requires a new round of testing and validation when we should be able to rely on a piece of software the behave the same way since the last time we touched it.

[recursive]

> Why should these developers rebuild a core piece of their stack every few months?

That's what they signed up for when established a hard dependency on an subscription online-only LLM model.

[BoorishBears]

If they were on open weights, at some point the provider would deprecate it, probably with worse notice

And self-hosting would probably have been more expensive unless they had massive volume: Deepseek V3.x would have been the comparable open weight model for the performance and isn't that cost effective until hosted across multiple nodes with large batch sizes

[recursive]

Sounds like something you'd need to evaluate before adopting then.

[imhoguy]

This is how development looks like for many years now, constant rewrite on the horizon. I think LLM development hype surpassed Blockchain and JS frameworks craze of decade ago.

[askvictor]

It's kind of the same problem with cloud in general (though that moves much slower).

If you want to be sure to be in control, then host it yourself

[vjsrinivas]

Its almost a given considering how fast this field moves. Also, what kind of workflow structure would someone have that a single specific model is the only one that would perform acceptably?

[samuelknight]

Programs are tightly shaped to their dependencies and software frequently breaks when bumping a dependency versions. That's why we have package managers that are carefully built around lock files. Models should be thought of like a dependency, not just an endpoint to a workflow.

[Capricorn2481]

These are AI models designed to be non deterministic. If upgrading from GPT 5.5 > 5.6 breaks your entire workflow, you shouldn't be using AI to begin with

[palmotea]

> Why should these developers rebuild a core piece of their stack every few months. Switching out a model requires a new round of testing and validation when we should be able to rely on a piece of software the behave the same way since the last time we touched it.

Because fuck you, that's way. /s

There's a massive amount of contempt from a lot of software businesses for their customers, and it's just getting worse with LLM models.