alt Hacker NewsIsn’t a modern LLM with thinking tokens fairly goal directed? But yes, we hallucinate in our sleep while LLMs will hallucinate details if the prompt isn’t grounded enough.
Replies
tovej • yesterday at 4:16 PM
Assuming this is not a rhetorical question: no, it is not. The only "goal" is to maximize plausibility.
➕ show 1 reply
The thing about dream logic is that it can be a completely rational series of steps, but there's usually a giant plot hole which you only realise the second you wake up.
This definitely matches my experience of talking to AI agents and chatbots. They can be extremely knowledgeable on arcane matters yet need to have obvious (to humans) assumptions pointed out to them, since they only have book smarts and not street smarts.