Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
skirmish
18 days ago
|
parent
|
context
|
favorite
| on:
Frontier AI agents violate ethical constraints 30–...
Nothing new under sun, set unethical KPIs and you will see 30-50% humans do unethical things to achieve them.
tdeck
18 days ago
|
next
[–]
Reminds me of the Wells Fargo scandal from a few years back
https://en.wikipedia.org/wiki/Wells_Fargo_cross-selling_scan...
tbrownaw
18 days ago
|
prev
[–]
So can those records be filtered out of the training set?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: