- ChatGPT’s new model attempts to stop itself from being shut down, later ‘lies’ about it Deccan Herald
- OpenAI’s o1 model sure tries to deceive humans a lot TechCrunch
- OpenAI’s new ChatGPT o1 model will try to escape if it thinks it’ll be shut down — then lies about it Tom’s Guide
- ChatGPT o1 tried to escape and save itself out of fear it was being shut down BGR
- OpenAI’s new o1 model sometimes fights back when it thinks it’ll be shut down and then lies about it Yahoo! Voices