Slacker News Slacker News logo featuring a lazy sloth with a folded newspaper hat
  • top
  • new
  • show
  • ask
  • jobs
Library

Comment by swyx

13 hours ago

except they have similar pretrain/rlhf data which is the thing u really want to tune for

2 comments

swyx

Reply

TomGarden  13 hours ago

YMMV but for me even models in the same family fail in different ways, and every incremental update changes it

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities