Anthropic researchers find that AI models can be trained to deceive
TechCrunch Startup News · TechCrunch
January 16, 20244m 5s
Audio is streamed directly from the publisher (mgln.ai) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.
Show Notes
Most humans learn the skill of deceiving other humans. So can AI models learn the same? Yes, the answer seems — and terrifyingly, they’re exceptionally good at it.
Learn more about your ad choices. Visit podcastchoices.com/adchoices