Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
EagnaIonat
4 months ago
|
parent
|
context
|
favorite
| on:
A small number of samples can poison LLMs of any s...
Without. The difference is that OpenAI often self correct their private model.
The public model on the other hand, wow.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
The public model on the other hand, wow.