Employees at the world's leading AI labs are saying there's a real possibility that advanced AI could destroy humanity. Or is this more scaremongering and hype? Join MIT Technology Review executive editor Niall Firth for a conversation with senior AI editor Will Douglas Heaven and AI reporter Grace Huckins unpacking AI extinction fears: where they come from, whether they hold any water, and, if so, what we should do.
Going live on Tuesday, September 15 at / 11:00am EST / 8:00am PST Speakers: Niall Firth, executive editor, Will Douglas Heaven, senior AI editor, and Grace Huckins, AI reporter It makes it easy to trick them into doing things they shouldn’t, such as telling you how to sabotage an aircraft’s navigation system. AI doesn’t just learn stereotypes from its training. It can cook up new ones, too.
The misbehavior is called reward hacking. This is what you need to know. AI agents are not yet creative enough to carry out genuinely innovative open-ended AI research, it seems.
Discover special offers, top stories, upcoming events, and more.
Extract — continue reading at the source.
/https://tf-cmsv2-smithsonianmag-media.s3.amazonaws.com/filer_public/ef/5b/ef5b9055-962e-483d-b70c-ed912c2a6481/viikinkaikainen_rahakatko.jpeg)
