“Folk are getting dangerously attached to AI that always tells them they’re right”
I don’t see this as particularly distinguishable from a large volume of social media interactions generally. Maybe we’ve achieved AGI after all.
www.theregister.com/2026/03/2…
!["Overall, deployed LLMs overwhelmingly affirm user actions, even against human consensus or in harmful contexts," the team found.&10;&10;As for how AI sycophancy affects humans, the team had a considerable sample size of 2,405 people who both roleplayed scenarios and shared personal instances where a potentially harmful decision could have been made. AI influenced participant judgments across three different experiments, they found.&10;&10;"Participants exposed to sycophantic responses judged themselves more 'in the right,'" the team said. "They were [also] less willing to take reparative actions like apologizing, taking initiative to improve the situation, or changing some aspect of their own behavior."](https://cdn.uploads.micro.blog/275515/2026/6bd0078b8d.jpg)