Yes, but hardly ever at Astra, because it usually gets the job done. Definitely at worse models when you give them very clear instructions and goals to follow and they respond telling you that the job has been completed perfectly, verified byte-identical, all tests pass, etc etc and you look at it and it’s a pile of garbage.

Only when I am on the phone, I like my agent on the computer not on the smart phone. It is too in your face.

All the time. Whenever Claude proposes some pansy-ass half-measure, I'll respond "F___ THAT," and Claude immediately knows I'm not playing.

All the time. Like in real life, curse words are the most meaning-dense. When Claude suggests some pansy-ass half-measure, I respond with "F___ THAT," and right away it knows I'm not playing.

I do very sparingly, same as with humans.

I also give them praise, and sometimes give them pep talks. Like, hey, I know you can do this. Stop asking me for feedback, make good decisions, and let me know when you're done.