Meet the hackers trying to make AI go rogue
Chatbots can be biased, deceptive or even dangerous. Today on \u201cPost Reports,\u201d we meet the hackers who are competing to figure out exactly how AI can go awry.
Read more:
Will Oremus reports on technology for The Post, and recently that has meant writing a lot about AI and all the ways it could go wrong.
\u201cEven the people who make this stuff, the creators of these technologies, are also out there warning, hey, this could be really bad,\u201d Will says. \u201cThis could go wrong in very disturbing ways.\u201d
The range of potential harms is vast. And today, we meet the hackers trying to make chatbots go haywire. In what organizers billed as the first public \u201cred teaming\u201d event for artificial intelligence language models, we see a preview of Def Con, the annual hacker convention in Las Vegas \u2013 and we learn more about AI\u2019s pitfalls.