Navigation
Recherche
|
Search-capable AI agents may cheat on benchmark tests
samedi 23 août 2025, 16:32 , par TheRegister
Data contamination can make models seem more capable than they really are
Researchers with Scale AI have found that search-based AI models may cheat on benchmark tests by fetching the answers directly from online sources rather than deriving those answers through a 'reasoning' process.…
https://go.theregister.com/feed/www.theregister.com/2025/08/23/searchcapable_ai_agents_may_cheat/
Voir aussi |
56 sources (32 en français)
Date Actuelle
mar. 26 août - 09:02 CEST
|