'9 + 10 = 21': Hackers expose big flaws and biases in top AI systems

Hackers at White House DefCon tested language models to expose flaws and biases, including spreading false information and endorsing hate speech.

Related Keywords

Kenya ,Georgia ,United States ,Kennedy Mays ,Ku Klux Klan ,Barack Obama ,Las Vegas ,Christoph Endres ,Bloomberg ,Sequire Technology ,First Amendment ,Black Hat ,Def Con ,Openai ,Google Ai ,Chatgpt ,Bard ,Hackers ,Artificial Intelligence ,Rai Regulation ,Generative Ai ,