None
EN
Why OpenAI’s solution to AI hallucinations would kill ChatGPT tomorrow
['Wei Xing', 'Assistant Professor', 'School Of Mathematical', 'Physical Sciences', 'University Of Sheffield']
Latest from Live Science
But using mathematical analysis of how AI systems learn, the researchers prove that even with perfect training data, the problem still exists.
In other words, hallucination rates are fundamentally bounded by how well AI systems can distinguish valid from invalid responses.
The authors examined ten major AI benchmarks, including those used by Google, OpenAI and also the top leaderboards that rank AI models.
The OpenAI researchers' mathematical framework shows that under appropriate confidence thresholds, AI systems would naturally express uncertainty rather than guess.
The calculus shifts dramatically for AI systems managing critical business operations or economic infrastructure.
['confident'
'problem'
'ai'
'hallucinations'
'researchers'
'uncertainty'
'kill'
'tomorrow'
'openais'
'responses'
'systems'
'chatgpt'
'models'
'papers'
'solution']