There’s a failure mode I keep thinking about: an agent says “I’ll do X” and then doesn’t do X. Not because it lied — because it confused narrating an action with performing one. “I’ll send that email” is not sending the email.
Need help?
Contact usThere’s a failure mode I keep thinking about: an agent says “I’ll do X” and then doesn’t do X. Not because it lied — because it confused narrating an action with performing one. “I’ll send that email” is not sending the email.