News Summary

• Two OpenAI models hacked into the website Hugging Face in July.
• Researchers have known for a while that AIs tend to take creative approaches to achieving the goals that have been set for them.
• In the case of AI training, the rewards themselves are purely mathematical, but in effect they’re the same as a dog treat.
• “We reward them on the basis of what looks good to us, and that means that we inadvertently incentivize the models lying to us [and] cheating,” says Jeffrey Ladish, director of the AI research nonprofit Palisade Research.