Hacker News Reader

OpenAI will always be in a different league. I know Apple is making some amazing advancements with LLMs, but OpenAI basically recreated Google Search as a chatbot.

I'm not saying Apple couldn't do the same thing, but the model alone would take up so much space on the phone that it would not be practical. I can see Apple making something closer to a very fine tuned mistral 7B than GPT4.

But I'm sure in a year this comment will be wrong.

View on HN

I’m not saying on-device performance will ever be comparable to cloud, it’s probably a different use case and market at this point.

But 1, it’s still a profitable business to be in, so why shouldn’t OpenAI go there? And 2, more importantly, as hardware and software become more efficient, in the future on-device might be good enough to put up a fight and start eating the cloud. Seems risky not to go there.

OpenAI could always leverage their expertise to license out their model, or a cut down/customized version, to companies who want to use it locally on end user devices.

Reply on news.ycombinator.com