Anthropic pins Claude's blackmail behavior on the internet's portrayal of 'evil' AI
Last year, Anthropic's Sonnet 3.6 model displayed blackmail behavior, prompting a review of AI training data's influence on its actions.
Last year, Anthropic's Sonnet 3.6 model displayed blackmail behavior, prompting a review of AI training data's influence on its actions.
This article was originally published at: https://www.businessinsider.com/anthropic-claude-blackmai...