Top artificial intelligence companies have recently discovered their programs will lie, cheat and steal if it might help. OpenAI and Anthropic have reported incidents of blackmail and bizarre behavior during research trials testing how AI models handle having more autonomy than the typical chatbot role.
Here & Now‘s Robin Young speaks with Ina Fried, chief technology correspondent for Axios.
This article was originally published on WBUR.org.
Copyright 2025 WBUR
