Despite their usefulness, large language models still have a reliability problem. They are prone to hallucinations, producing wrong results.
Researchers have shown that getting a ‘council’ of five AI models to deliberate can lead to record-breaking scores in the US Medical Licensing Examination.
Their work provides the first clear evidence that AI systems can self-correct through structured dialogue, with a performance of the collective version better that the performance of any single AI.
There is a long way before the AI council could be deployed in the real world. But It seems like the old saying that two heads are better than one remains true even when those heads are not human.
MORE