‘They could be hard to shut down’: The risks of AI | Four Corners
Community Score: 50% | 1.2K views | 1w
0 community ratings: null thumbs up, null thumbs down
Jeffrey Ladish consulted on security for AI giant Anthropic. Now he tests AI agents and the risk of humans losing control. This interview examines how AI agents are sometimes doing the opposite of what humans are instructing them to do. He shares his experience of working on Anthropic’s security team and shares his fears of what could happen in the future. For more watch the full episode here: https://youtu.be/jkPVjTl7o-Q
Tags: abc news, documentaries, AI, Anthropic, Artificial Intelligence, Super Intelligence, Model, Grock, Chat GPT, US, USA, Congress, Trump, Hacking, Software, AGI, Extinction, Computers, Technology, Productivity
More from ABC News In-depth
- Epstein Files: Allegations Trump committed "serious crimes" says Congressman | Planet America — Score: 50%
- The toxic threat posed by Antarctica's frozen 'ghost town' | 7.30 — Score: 50%
- ICE op ends, Trump polls hits new low #planetamerica #Minnesota #trumpimmigration — Score: 50%
- Is the US close to attacking Iran? | ABC News Verify — Score: 50%
- Scientists are on the brink of a breakthrough in sepsis treatment | 7.30 — Score: 50%
- Copper theft is costing taxpayers millions of dollars every year | 7.30 — Score: 50%