Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
visarga
on May 3, 2022
|
parent
|
context
|
favorite
| on:
OPT: Open Pre-trained Transformer Language Models
A well trained GAN has 50% chance of finding if the generate image is fake or not. But you can't do imperceptible changes on text like you for images.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: