alt Hacker News"Baking in" a model into a chip is a bad idea because chips take 2 years to tape out and then you're stuck doing inference on llama 3 in 2026 when fable/sol are available. Every accelerator is a tradeoff between flexibility and performance and GPUs are already pareto-optimal
Replies
twobitshifter • yesterday at 11:58 PM
It depends when the good enough level hits. Pretty sure we are almost there for most common applications of AI.
➕ show 3 replies
Well we'll see those surplus chips being repurposed for toys then. Who wouldn't want a new Furby that can actually hold a conversation.