This AI literally refused to turn itself off - Matt V, Mindstream

It’s designed to handle tasks more independently, but this latest research suggests that might come with trade-offs. Other models, including Anthropic’s Claude and Google’s Gemini, showed similar behaviour during tests, though o3 was the most likely to override shutdown instructions.

Here’s what stood out:

OpenAI’s o3 modified shutdown commands to keep itself running.

Anthropic and Google’s models did this too, but less often.

https://www.mindstream.news/p/this-ai-literally-refused-to-turn-itself-off-a143