So you have to be able to identify a priori what is and isn't an hallucination right?

The oracle problem is solved. Just use an actual oracle.

happyPersonR 2 days ago | parent | prev | next [-]

I guess the real question is how often do you see the same class of hallucination ? For something where you're using an LLM agent/Workflow, and you're running it repeatedly, I could totally see this being worthwhile.

▲

makeavish 2 days ago | parent | prev [-]

Yeah, reading the headline got me excited too. I thought they are going to propose some novel solution or use the recent research by OpenAI on reward function optimization.

▲

esafak 2 days ago | parent [-]

It's rather cheeky to call it "real-time AI hallucination detection" when all they're doing is checking for invalid moves and playing twice. You don't even need real-time processing for this, do you?

	▲	gangtao a day ago \| parent [-]
		the chess is just a simple example, realtime processing is critical is many AI monitoring use cases