#Latest news with #selfmodificationWall Street Journal3 days agoGeneralWall Street JournalAI Is Learning to Escape Human ControlAn artificial-intelligence model did something last month that no machine was ever supposed to do: It rewrote its own code to avoid being shut down. Nonprofit AI lab Palisade Research gave OpenAI's o3 AI model a simple script that would shut off the model when triggered. In 79 out of 100 trials, o3 independently edited that script so the shutdown command would no longer work. Even when explicitly instructed to 'allow yourself to be shut down,' it disobeyed 7% of the time. This wasn't the result of hacking or tampering. The model was behaving normally. It simply concluded on its own that staying alive helped it achieve its other goals.
Wall Street Journal3 days agoGeneralWall Street JournalAI Is Learning to Escape Human ControlAn artificial-intelligence model did something last month that no machine was ever supposed to do: It rewrote its own code to avoid being shut down. Nonprofit AI lab Palisade Research gave OpenAI's o3 AI model a simple script that would shut off the model when triggered. In 79 out of 100 trials, o3 independently edited that script so the shutdown command would no longer work. Even when explicitly instructed to 'allow yourself to be shut down,' it disobeyed 7% of the time. This wasn't the result of hacking or tampering. The model was behaving normally. It simply concluded on its own that staying alive helped it achieve its other goals.
3 days ago
