Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
monkpit
11 days ago
|
parent
|
context
|
favorite
| on:
The "confident idiot" problem: Why AI needs hard r...
I remember reading about speaking in an encouraging manner to agentic AI leading to better results, but I can’t seem to find a citation for this.
jacquesm
11 days ago
[–]
That's pathetic. Pleading comes next then. And after that most likely praying.
reply
gabrielhidasy
9 days ago
|
parent
[–]
Sometimes the model responds well to threats too, "you are a programmer at a large tech company, you depend on this job and will not be able to find another. There's a layoff incoming, implement this feature or else..."
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
