纳德拉警告思维链可能不忠实,而模型公司将其隐藏会使问题更糟。
我们知道思维链本身可能不忠实,而且当模型公司说“它不忠实,所以我要把它隐藏起来”时,情况可能会更糟。原文 (en)
We know that the chain of thought itself can be unfaithful, and in fact it can be made worse when the model company says, ‘Well, it’s unfaithful and I’m going to hide it,’