Thread

Show HN: Jevgpt – reinventing the wheel with another wheel

26 points · 4 comments · kunggaochicken

nico · 1790384224 · focus · HN ↗
This is amazing. I don't think I fully understand how it works, but the core of having Jev (or some classifier), generate the words/tokens it's going to output by picking/classifying the words/tokens, is very cool
Where do you see the biggest potential improvement gains?
1. kunggaochicken · 1790639915 · focus · HN ↗
  honestly i dont actually expect it to improve anything - kinda did it as a rebellious shower thought when the jev homescreen said "we are not a chatbot"
  the underlying mechanism has to sample tokens (1000/90000 for openai's tokenizer) by some shallow heuristic to build the decision pool (more details are in <a href="https://github.com/giga-james/jevgpt/blob/main/docs/experiments.md" rel="nofollow">https://github.com/giga-james/jevgpt/blob/main/docs/experime... !), while standard autoregressive models have access to the entire token vocabulary to predict the next word

Unofficial Hacker News client; not affiliated with Y Combinator.