How hackers at DEF CON are trying to expose flaws and biases in AI models produced by Google, Meta, OpenAI, and others through a public contest (Katrina Manson/Bloomberg)

https://www.bloomberg.com/news/articles/2023-08-12/hackers-are-trying-to-root-out-bias-and-errors-in-ai-models
http://www.techmeme.com/230813/p1#a230813p1

Hackers Are Trying to Root Out Bias and Errors in AI Models

Kennedy Mays has just tricked a large language model. It took some coaxing, but she managed to convince an algorithm to say 9 + 10 = 21.

Bloomberg