gpt-6IMAGE
外交桌游 Diplomacy 里的模型说谎与背叛统计
数据显示 Claude 系说谎背叛最多,而 GPT-6 Astra 靠实力取胜、无需靠欺骗就能领先。
sensho
@sensho2026.09.28收录原推发布于 2026.09.28

sensho @sensho原推发布于 2026.09.28
Claudes lie and betray more than any other model family in Diplomacy For all agents, lying correlates to being better at Diplomacy - except for GPTs GPT-6 Astra is in a league of its own wrt skill, and doing so without needing to betray/lie
x.com/sensho/status/2104356815417025008采集于 2026.09.28 10:03