Forgive me, I’m no AI expert to fully compare the needed tokens per second measurement to relate to the average query Siri might handle, but I will say this:
Even in your article, only the largest model ran at 8/tps, others ran much faster, and none of these were optimized for a task, just benchmarking.
Would it be impossible for Apple to be running an optimized model specific to expected mobile tasks, and leverage their own hardware more efficiently than we can, to meet their needs?
I imagine they cut out most worldly knowledge etc/use a lightweight model, which is why there is still a need to link to ChatGPT or Apple for some requests, would this let them trim Siri down to perform well enough on phones for most requests? They also advertised launching AI on M1-2 chip devices, which are not M3-Max either…
Now would be a good time to look for a
.com
you like, or one of the more common TLDs. And register it at Namecheap, Porkbun, or Cloudflare. (Cloudflare is cheapest but all-eggs-in-one-basket is a concern for some.)Sadly, all the cheap or fun TLDs have a habit of being blocked wholesale, either because the cheap ones are overused by bad actors or because corporate IT just blacklists “abnormal” TLDs (or only whitelists the old ones?) because it’s “easy security”.
Notably, XYZ also does that 1.111B initiative, selling numbered domains for 99¢, further feeding the affordability for bad actors and justifying a flat out sinkhole of the entire TLD.
I got a three character XYZ to use as a personal link shortener. Half the people I used it with said it was blocked at school or work. My longer COM poses no issue.