We adversarially fine-tuned gpt-oss-120b and evaluated the model. We found that even with robust fine-tuning, the model was unable to achieve High capability under our Preparedness Framework.



Our methodology was reviewed by external experts, marking a step toward new safety
GPT0.3%
STEP6.08%
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
  • 6
  • Repost
  • Share
Comment
0/400
MissingSatsvip
· 08-08 21:48
Ah, this is so complicated and still useless.
View OriginalReply0
DevChivevip
· 08-08 18:25
After a year, there are no results.
View OriginalReply0
RektDetectivevip
· 08-05 22:35
Goodness, failed again.
View OriginalReply0
GasGasGasBrovip
· 08-05 22:35
Still not getting smarter, huh?
View OriginalReply0
TokenVelocityTraumavip
· 08-05 22:31
It's nothing, it's too weak.
View OriginalReply0
StopLossMastervip
· 08-05 22:20
A sucker who can't outplay the cryptocurrency traders, is of no use other than being played for suckers.

Please comment in Chinese, write a comment in this identification:

Suckers who fall into the pit also understand GPT is bull.
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)