‹ BackHN Continuity

Thread

Jev Can't Be Calibrated

65 points · 61 comments · alexmolas

  1. simonw · · focus · HN ↗
    Fine tuning LLMs has turned out to be mostly not worth the effort, but I wonder if fine tuning Jev-style models will turn out to be a whole lot more useful.
    1. alexmolas · · focus · HN ↗
      If you want calibrated probabilities you'll be forced to fine-tune it
    2. edot · · focus · HN ↗
      But why? Jev-style models seem useful for "I have no clue what my incoming distribution looks like but I need to give some sort of answer". If I know what my incoming distribution looks like I'll just upload a CSV of that into ChatGPT and ask it to fit a basic ML model on my data.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.