Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
jazzyjackson
11 days ago
|
parent
|
context
|
favorite
| on:
GPT-5.2
Yea you might have to convince it someone is in mortal danger or something
int_19h
11 days ago
[–]
You're talking about a model that will notoriously refuse to say a racist word even if you tell it that it's the only way to prevent a nuclear apocalypse.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
