• Sign in
  • Sign up 
  • Welcome
  • FAQ
  • Block Explorer 
  • Night Mode
  • Stolen Accounts Recovery 
  • Change Account Password 
  • Vote for Witnesses 
  • Hive Proposals 
  • OpenHive Chat 
  • Developer Portal 
  • Hive Whitepaper 
  • Privacy Policy
  • Terms of Service
logo
  • Posts
  • Proposals
  • Witnesses
  • Our dApps
LoginSign up
You are viewing a single comment's thread from:

RE: LeoThread 2025-01-30 12:14

  • View the full context
  • View the direct parent
tokenizedsociety (69)in LeoFinance • 9 months ago

DeepSeek R1's recipe to replicate o1 and the future of reasoning LMs

Nathan Lambert breaks down the recipe for R1 and talks through what it means for us now and for the field broadly. Specifically, he focuses on the interesting application of reinforcement learning.

#technology #ai #deepseek #r1 #nathanlambert

9 months ago in LeoFinance by tokenizedsociety (69)
$0.00
    Reply 0
    Sort:  
  • Trending
    • Trending
    • Votes
    • Age