In the conversation, the AI fails to recognize the reference to the Sleeping Beauty experiment and gives an answer based on the words used. This suggests that it may not be modeling the problem structure. Another example is given where the AI is asked if it would hurt to touch a cast iron skillet that had been out of the oven for a while. The AI should have known the correct answer because it doesn't make silly mistakes without reason.
The Artificial Intelligence landscape is changing with remarkable speed these days, and the capability of Large Language Models in particular has led to speculation (and hope, and fear) that we could be on the verge of achieving Artificial General Intelligence. I don't think so. Or at least, while what is being achieved is legitimately impressive, it's not anything like the kind of thinking that is done by human beings. LLMs do not model the world in the same way we do, nor are they driven by the same kinds of feelings and motivations. It is therefore extremely misleading to throw around words like "intelligence" and "values" without thinking carefully about what is meant in this new context.
Blog post with transcript: https://www.preposterousuniverse.com/podcast/2023/11/27/258-solo-ai-thinks-different/
Support Mindscape on Patreon.
Some relevant references:
See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.