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

Comment by zozbot234

7 hours ago

> Mythos is a much bigger pre train

Do we have data to substantiate that claim?

1 comment

zozbot234

Reply

solenoid0937  7 hours ago

It's pretty common knowledge. Spud is the only other PT comparable with Mythos.

Both Spud and Mythos can also scale via inference time compute.

Meta simply did not have enough compute online, long enough ago, to have a similar PT.

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities