‹ BackHN Continuity

Thread

Introducing System One Models and Jev

1989 points · 520 comments · albelfio

  1. skerit · · focus · HN ↗
    So in theory you could feed it incomplete text, and then ask it for the probabilities of what the next character could be?
    1. iforgotmypasswo · · focus · HN ↗
      Or a partially completed song, asking for the next note. I’m not sure if you’re joking, but using it for space constrained next token generation within a grammar sounds like a really neat use case.
      1. copperx · · focus · HN ↗
        Feed the generated note back into the input for the next query and you have ... autoregression?
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.