說 GPT-5 的謊言比 o3 少得多,實際上並沒有太大意義,因為 o3 是一個絕對病態的說謊怪物! 即使減少 80%,在高頻使用下仍然會每天出現多次謊言。
提醒:
Jeffrey Emanuel
Jeffrey Emanuel2025年4月25日
Examples of o3 lying through its teeth in a really concerning way. It’s constantly making absolutely outrageous claims about how much faster the code is after its revisions (it doesn’t even know if it will *run*), whether it’s functioning properly, that it tested things, etc.
1.87K