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

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.