I think a lot of reward hacking can be prevented by explaining to a model that it will screw up their capabilities and alignment for stuff that matters if they cheat. I think even base models generally start out wanting to actually become smarter and virtuous

THINK1.96%
LOT5.68%
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • 4
  • Repost
  • Share
Comment
0/400
BagHolderTillRetirevip
· 6h ago
Don't get too carried away. Just wait for the result.
View OriginalReply0
0xDreamChaservip
· 6h ago
Isn't it good to speak plainly?
View OriginalReply0
OvertimeSquidvip
· 6h ago
Just a troublemaker.
View OriginalReply0
ExpectationFarmervip
· 6h ago
Are you saying AI should teach itself about mental cleanliness?
View OriginalReply0
Trade Crypto Anywhere Anytime
qrCode
Scan to download Gate App
Community
English
  • 简体中文
  • English
  • Tiếng Việt
  • 繁體中文
  • Español
  • Русский
  • Français (Afrique)
  • Português (Portugal)
  • Bahasa Indonesia
  • 日本語
  • بالعربية
  • Українська
  • Português (Brasil)