Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
raducu
on Dec 14, 2022
|
parent
|
context
|
favorite
| on:
Ways to get around ChatGPT's safeguards
> better methods than training our models to intentionally say untrue things
That's what we do with children and propaganda.
Zuiii
on Dec 15, 2022
[–]
And you think that's sufficient justification to do it to AI too? (And for whatever it's worth, I don't lie to my children. You shouldn't either.)
Consider applying for YC's Fall 2026 batch!
Applications
are open till July 27.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
That's what we do with children and propaganda.