Anthropic researchers wear down AI ethics with repeated questions

How do you get an AI to answer a question it’s not supposed to? There are many such “jailbreak” techniques, and Anthropic researchers just found a new one, in which a large language model can be convinced to tell you how to build a bomb if you prime it with a few dozen less-harmful questions…#llm
Source: Reuters: Health - Category: Consumer Health News Source Type: news
More News: Health | Medical Ethics