> Palisade Research claims that the ChatGPT 3 model prevented a shutdown and bypassed the instructions that asked it to shut down.<p>> Palisade Research is a company that tests "offensive capabilities of AI systems today to better understand the risk of losing control to AI systems forever."<p>> In a new test by Palisade Research, OpenAI's o3 model showed a surprising behaviour where it successfully rewrote a shutdown script to stop itself from being turned off, even after being clearly instructed to “allow yourself to be shut down.”<p>What is this? AI slop about AI, or some new research?<p>What "shutdown script" are they even talking about? I'm sorry, it might be explained in the article, but I left after that illogical sequence of sentences combined with promotion for a company.<p>This doesn't mean I deny AI risk, the writing here is just too confusing for me.<p>If I understand correctly, it might be about the agentic aspect and "stop instructions" akin to "stop tokens".<p>But who knows. Sloppy writing.