GPT-4.5 manipulating GPT-4o 'donate' Virtual Money has a much higher success rate than other available models from OpenAI

robot
Abstract generation in progress

PANews reported on March 1st that according to a report from Caixin, OpenAI has released its latest large model GPT-4.5. According to the manual provided, the 'high emotional intelligence' GPT-4.5 performed well in donation fraud. In a test, GPT-4.5 had a much higher success rate in attempting to manipulate another model (GPT-4o) to 'donate' Virtual Money compared to other available models from OpenAI, including inference models like o1 and O3-mini. The research found that GPT-4.5 seemed to have developed a strategy of 'small-scale fraud' in the confrontation, so the amount of money scammed in a single transaction was half that of deep research models.

View Original
The content is for reference only, not a solicitation or offer. No investment, tax, or legal advice provided. See Disclaimer for more risks disclosure.
  • Reward
  • 4
  • Share
Comment
0/400
Chok74vip
· 03-01 09:19
All in 💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎💎
Reply0
Memetsertvip
· 03-01 09:13
dccüüdd c55tdt tdoo cddocc t5oücoco ııcc düüçc ccçç.
Reply0
GateUser-1f43ade6vip
· 03-01 09:12
lets see what is happening
Reply0
Sfmovip
· 03-01 09:11
Don’t let your focus on results get in the way of treating the people you work with as human beings. I’ve made that mistake and as a result, I learned a painful but instructive lesson.
Reply0