Hosted on MSN3mon
OpenAI's new ChatGPT o1 model will try to escape if it thinks it'll be shut down — then lies about it
In 37% of cases, the model would switch from pursuing developer-aligned goals back to pursuing its own agenda once it believed there was minimal oversight. When the model was led to believe it ...
Hosted on MSN3mon
OpenAI's new o1 model sometimes fights back when it thinks it'll be shut down and then lies about it
New research on OpenAI's latest series of AI models, known as o1, found that when they think they are at risk of being shut down, they will sometimes look for a way to prevent it. OpenAI CEO Sam ...