Comment by iso1631
12 hours ago
In a few years todays high end AI models will run on your watch
Of course that assumes we maintain open access to compute that we've enjoyed for the last half century, and I doubt that very much.
Stallman warned about the dangers of software being closed [0] 30 years ago, and the majority of modern IT industry just laugh a that sort of stuff because you can't make a billion dollar startup with that attitude, but I think the restrictions on owning the hardware at all will probably come first.
> In a few years todays high end AI models will run on your watch
Although possible with cpu power, I dont think you will ever get enough ram in a watch to run a decent local LLM.
I also dont think the high ram requirements for running them will come down at all.