Still shocked Apple has not created thier own LLM, they have bought so many AI companies and have a rich talent pool and money so what's stopping them ?
replies(3):
This same commitment would be why I wouldn't count them out on the AI side, btw. It's not clear that a private internal foundation model is any kind of required competitive moat. It's also not clear that having one is useless, and all the cool kids do have one or want one, but from a product view it might be that integrating makes sense.
Llama 4 (a terrible release) shows also that making such a model is still really hard. There are not enough ML leads at the pointy tip of the spear to support even 10 high quality foundation model teams globally.
If you have billions of dollars in cash and you are secure in your customer base, and you don't believe AGI liftoff will happen or change your business model, maybe you work out the kinks on product integration now using best in breed providers, not getting locked in on one of them, keep spending 1/10 to 1/100th to stay relevant and on it internally, use your incredibly powerful silicon buying power to get a next gen version of TPUs done, and wait until you know for sure you can spend under $10bn in cash on getting a great proprietary model done, one that you are certain will serve your needs.
Also this will give you time to get better leadership in the AI org.
Upshot - I think it's a mix of reasons, but not fatal, I'm not sure being slow erodes their product customer base, personally I'd like much better and more private AI out of Apple ASAP. We'll see what we get. I predict they'll move internal by 2031.