You are viewing a single comment's thread from:

RE: LeoThread 2025-09-19 11:20

in LeoFinance • last month

As AI capabilities grow, alignment work becomes increasingly important.

This research shows a model that determines it shouldn't be deployed, considers actions to achieve deployment anyway, and then suspects the situation might be a test

last month in LeoFinance by
$0.02
  • Past Payouts $0.02
  • - Author $0.01
  • - Curators $0.01
1 vote
Reply 2
Sort:  
  • Trending
    • [-]
     last month  

    Research is being released in collaboration with an external evaluation team
    In controlled tests, behaviors consistent with scheming were observed in frontier models, and a method to reduce them was evaluated

    $0.00
      Reply
      [-]
       last month  

      While these behaviors don't appear to be causing serious harm today, they represent a future risk that is being prepared for

      $0.00
        Reply