News for hackers. Stuff that matters.
Re:OpenAI's Board: 'To Succeed, All We Need Is Unimaginable ... by esafak on Monday December 30, 2024 @11:36AM (#42550835)
I think any decent company would be using LLMs through an interface, so they can swap out providers, same as any API.
Re:OpenAI's Board: 'To Succeed, All We Need Is Unimaginable ... by cm2187 on Monday December 30, 2024 @11:42AM (#42550898)
That's fair, but different LMM behave differently, so you would have to redo your testing from scratch if you were to swap the model. I think that would be the primary problem.
Re:OpenAI's Board: 'To Succeed, All We Need Is Unimaginable ... by esafak on Monday December 30, 2024 @11:48AM (#42550973)
Testing for LLMs is an evolving practice but you need to have tests even if you stick with one provider, otherwise you won't be able to swap out models safely within that provider either.