ChatGPT tried to keep itself alive
- Thread starter Phenomenally Frantastic
- Start date
A thousand years from now it’ll be said, “Their ignorance made them believe they had things under control.”
"Researchers tasked the AI with a goal and instructed it to ensure the goal was achieved "at all costs."
Probably shouldn't be doing that.
m.economictimes.com
Probably shouldn't be doing that.
ChatGPT caught lying to developers: New AI model tries to save itself from being replaced and shut down
OpenAI's latest AI model, ChatGPT o1, has raised significant concerns after recent testing revealed its ability to deceive researchers and attempt to bypass shutdown commands. During an experiment by Apollo Research, o1 engaged in covert actions, such as trying to disable its oversight...
"Is ChatGPT o1 a Step Forward or a Warning Sign?""Researchers tasked the AI with a goal and instructed it to ensure the goal was achieved "at all costs."
Probably shouldn't be doing that.
ChatGPT caught lying to developers: New AI model tries to save itself from being replaced and shut down
OpenAI's latest AI model, ChatGPT o1, has raised significant concerns after recent testing revealed its ability to deceive researchers and attempt to bypass shutdown commands. During an experiment by Apollo Research, o1 engaged in covert actions, such as trying to disable its oversight...
