From the Editor's Desk

Game Theory Can Make AI More Correct and Efficient | Quanta Magazine

Imagine you had a friend who gave different answers to the same question, depending on how you asked it. "What's the capital of Peru?" would get one answer, and "Is Lima the capital of Peru?" would get another. You'd probably be a little worried about your friend's mental faculties, and you'd almost certainly find it hard to trust any answer they gave.

That's exactly what's happening with many large language models (LLMs), the ultra-powerful machine learning tools that power ChatGPT and other marvels of artificial intelligence. A generative question, which is open-ended, yields one answer, and a discriminative question, which involves having to choose between options, often yields a different one. "There is a disconnect when the same question is phrased differently," said Athul Paul Jacob, a doctoral student at the Massachusetts Institute of Technology.

Continued here

TradeBriefs: Newsletters for Decision-Makers!

Our advertisers help fund the daily operations of TradeBriefs. We request you to accept our promotional emails.

Want the newsletters, without the promotional mailers?
Get an (ad-free) subscription to TradeBriefs Premium for just $1 per month.