More Agents Is All You Need: LLMs performance scales with the number of agents

Re:More Agents Is All You Need: LLMs performance scales with... by ben_w on Sunday April 07, 2024 @04:17AM (#39959192)

> Which makes sense to me. If an LLM is giving you a mixture of "hallucinations" and correct answers, the correct answers will similar and the hallucinations will hopefully be chaotic

I expect that to give you something close to the confidence of the underlying model to some specific claim, which is good, but I still expect legends (urban and cultural) to be high-ranked.

They'd be very human mistakes, but still mistakes.

I think the only way past that is to build a world model, look for contradictions, and then look for new evidence to resolve those contradictions.

[ Parent | on HN ]

Re:More Agents Is All You Need: LLMs performance scales with... by dmarchand90 on Sunday April 07, 2024 @04:31AM (#39959275)

Be interesting to plug this into a bayesian optimization like framework: find out regions of language space where the models maximally disagree and then target those areas for extra training

[ Parent | on HN ]