The researchers proposed using different chatbots to produce multiple answers to the same question and then letting them debate each other until one answer won out. Most researchers agree the problem is inherent to the “large language models” that power the bots because of the way they’re designed. Some firms are using human trainers to rewrite the bots’ answers and feed them back into the machine with the goal of making them smarter. If they don’t, the AI answer won’t even show up. Some leading AI researchers say hallucinations should be embraced.

Source: Washington Post May 31, 2023 11:40 UTC