Speaker unverified: belief

Transcript context

…We have to try to construct an incentive system where you should behave the same, just as you were saying with prompt engineering, behave with Claude like you would with other humans. It’s just good for the soul. Yeah. I think we added a thing at one point to the system prompt, where basically if people were getting frustrated with Claude, it got the model to just tell them that it can do the thumbs-down button and send the feedback to Anthropic. I think that was helpful. Because in some ways, if you’re really annoyed because the model’s not doing something you want, you’re just like, “Just do it properly.” The issue is you’re maybe hitting some capability limit or just some issue in the model, and you want to vent. Instead of having a person just vent to the model, I was like, they should vent to us, because we can maybe do something about it. That’s true. Or you could do a side with the artifacts, just like a side venting thing. All right. Do you want a side quick therapist?…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.