‹ BackHN Continuity

Thread

What if AI worked at 1.000.000 tokens per seconds?

7 points · 13 comments · echohive42

  1. ed · · 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. beej71 · · focus · HN ↗
      And yet somehow we all know that it's going to be laggier than ever. :)
      1. echohive42 · · focus · HN ↗
        i hope not :)
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.