The bottleneck with compute at the edge is (and will be) model size (both app download time and storage space on device). Stable Diffusion sits at about 2GB for fp16, Whisper Medium at 1.53GB, LLAMA is 120GB. Sure, Apple can ship an optimized model ( 1GB.
Transformer architecture optimized for Apple Silicon
201–210 of 342 posts
Re: Transformer architecture optimized for Apple Silicon
#202Earlier quoted context omitted.
why does this matter when we have cloud computing and high speed mobile internet? why does it need to be local
Because it's more seamless and then integrates into the Apple hardware ecosystem due to AirDrop and other integrations.
Imagine Google Sonar on Pixel phone with Pixel ear buds and more sensors and ChatGPT onboard.
Re: Transformer architecture optimized for Apple Silicon
#203i'd say within 5 years apple will have optimized apple silicon and their tech, along with language model improvements, such that you will be able to get gpt-4 level performance in the iPhone 19 with inference happening entirely locally. openai is doing great work and is serious competition, but I think many underestimate big tech. once they're properly motivated they'll catch up quick. I think we can agree that opena…
Re: Transformer architecture optimized for Apple Silicon
#204The bottleneck with compute at the edge is (and will be) model size (both app download time and storage space on device). Stable Diffusion sits at about 2GB for fp16, Whisper Medium at 1.53GB, LLAMA is 120GB. Sure, Apple can ship an optimized model ( 1GB.
That is not even taking into consideration that shipping your weights to the client is akin to giving your product away.
Re: Transformer architecture optimized for Apple Silicon
#205i'd say within 5 years apple will have optimized apple silicon and their tech, along with language model improvements, such that you will be able to get gpt-4 level performance in the iPhone 19 with inference happening entirely locally. openai is doing great work and is serious competition, but I think many underestimate big tech. once they're properly motivated they'll catch up quick. I think we can agree that opena…
Siri is still extremely basic and barely usable for anything besides starting a kitchen timer.
Re: Transformer architecture optimized for Apple Silicon
#206Earlier quoted context omitted.
That is not even taking into consideration that shipping your weights to the client is akin to giving your product away.
Wait, how is that fundamentally different from shipping binary code? Isn't that also akin to "giving your product away"?
I don't think you can pirate e.g. the Facebook app binary and make it your own.
Re: Transformer architecture optimized for Apple Silicon
#207i'd say within 5 years apple will have optimized apple silicon and their tech, along with language model improvements, such that you will be able to get gpt-4 level performance in the iPhone 19 with inference happening entirely locally. openai is doing great work and is serious competition, but I think many underestimate big tech. once they're properly motivated they'll catch up quick. I think we can agree that opena…
I'm not so sure. When is the last time apple came out something groundbreaking? Has there been anything since Tim Cook took over? Siri is still extremely basic and barely usable for anything besides starting a kitchen timer.
Re: Transformer architecture optimized for Apple Silicon
#208i'd say within 5 years apple will have optimized apple silicon and their tech, along with language model improvements, such that you will be able to get gpt-4 level performance in the iPhone 19 with inference happening entirely locally. openai is doing great work and is serious competition, but I think many underestimate big tech. once they're properly motivated they'll catch up quick. I think we can agree that opena…
I'm not so sure. When is the last time apple came out something groundbreaking? Has there been anything since Tim Cook took over? Siri is still extremely basic and barely usable for anything besides starting a kitchen timer.
M1 chips?
Re: Transformer architecture optimized for Apple Silicon
#209Earlier quoted context omitted.
> > Apple has a ridiculous, almost unfathomably deep moat for training and running [LLMs]... > Do they? I can completely fathom, given my own anecdotal experiences, how garbage Siri quality is today. Siri is a dead end. When Jobs bought Siri (what, 10 years ago?) he explicitly junked almost all the AI back end, mainly buying the speech recognition engine. I didn't understand why and still don't (but strangely he didn…
Jobs has been dead for over ten years
Re: Transformer architecture optimized for Apple Silicon
#210i'd say within 5 years apple will have optimized apple silicon and their tech, along with language model improvements, such that you will be able to get gpt-4 level performance in the iPhone 19 with inference happening entirely locally. openai is doing great work and is serious competition, but I think many underestimate big tech. once they're properly motivated they'll catch up quick. I think we can agree that opena…