Ask HN: Do you cuss at your agent? | Hacker News Reader

Ask HN: Do you cuss at your agent?

4 pointsak3914 comments

Do you vent your frustrations at your agent when it keeps making stupid mistakes and asinine assumptions or asks obvious questions?

I did it for the first time and I feel ashamed.

View on HN

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.

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.

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

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.

NO! I just prompt normally, and if that fails, hand-code or restart from scratch instead

Fuck yes, I do. Not the most effective way to get things done, but a bit cathartic. And no, the stochastic parrot does not have emotions. And yes, it sometimes does worse after being cursed at, but you’re generally better off forking/rolling back the convo to a point before it screwed up anyway. And other times strong language manages to provide the emphasis you need to get it to actually pay attention.

Anyway, why are you ashamed of it?

I felt ashamed because it fooled me into believing it had feelings like a living thing.

Ah.

I feel free to curse at it precisely because I’m confident it doesn’t have feelings, and it’s like swearing out loud at an inanimate object like when a shoddy screwdriver breaks, or strips a screw, or whatever.

Don’t blame the agent for not giving it the right requirements and skills to accomplish a task.

Sometimes upstream providers swap in lobotomized aggressive quants in order to shed load or cut costs. In that case the user is not to blame. And the agent is not so much to blame, either. Same as how you wouldn't blame a child for crashing a car.

It's the fucking provider who took your dollars and handed you back a shit sandwich in return.

I usually call the agent a Muppet when it does something fucking stupid. That might be my fault.

I'm usually polite, but I do use the agents instead of a stress ball ..

no, that's token waste.

when the ai would do something wrong, i'd rather use it as an opportunity to understand how i can prompt it better or engineer better ways get shit done.

i've literally had very rare, mostly zero issues with ai giving me slop over the last few months, once i took the time to undertand how to use these tools effectively instead of complaining.

hahaha, come on, why would you feel ashamed, at the end it does not really help to generate better answer, just spend the time writing better prompt rather than cursing an AI agent , at least maybe if you phrase the prompt well and structure it good, it migth give you a good answer

Reply on news.ycombinator.com