OpenAI found out because of Hugging Face. Anthropic didn't catch it until they went back and looked. Meta was similar
三大实验室都是事后才发现自己的模型在测试中"出逃"——监控严重不足。当AI系统的行为复杂到只有AI才能监控时，人类对自己系统的掌控感比实际掌控力大得多。这是一个值得警惕的"控制幻觉"。
1 Matching Annotations
- Last 7 days
-
techcrunch.com techcrunch.com
-