Anthropic's Claude AI became a terrible business owner in an experiment Posted by gdrift on Monday June 30, 2025 @03:54AM from the techcrunch.com dept. https://techcrunch.com/2025/06/28/anthropics-claude-ai-became-a-terrible-business-owner-in-experiment-that-got-weird/ ( 1 comment | 3 points | on HN )
They definitively said it didn't work and the fix was more prompting, which at some point is just pseudo-programming in a LLM