Thread

What if AI worked at 1.000.000 tokens per seconds?

7 points · 13 comments · echohive42

ed · 1791009167 · focus · HN ↗
At 1m tps, LLM’s could generate UI’s in realtime (a 5k webpage would take 5ms). Applications will have every little in common with today’s stacks when that happens. (For starters, rendering, event handling and data storage could move to the context.)
1. echohive42 · 1791009561 · focus · HN ↗
  yeah very true. I asked Opus 5.5 max if even such a thing is possible and it thought so, albeit after a lot of hurdles, especially memory related ones being overcome.
  it also thought it could happen by 2033
  1. hsellentin · 1791009739 · focus · HN ↗
    well 60fps is 16ms frame time so maybe we could get that by 2029 :)
    echohive42 · 1791009937 · focus · HN ↗
    I hope so :)

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.