Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
magicalhippo
3 months ago
|
parent
|
context
|
favorite
| on:
OpenAI has deleted the word 'safely' from its miss...
I assume so, just haven't tried the others yet. Main point was rather that the model can behave differently if the provider wanted, without any additional training.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: