Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
dotnet00
on May 3, 2022
|
parent
|
context
|
favorite
| on:
OPT: Open Pre-trained Transformer Language Models
If differentiating between real samples and generated ones were as straightforward as "training a GAN", detecting deep fakes would not be as big of a research topic as it is.
daenz
on May 3, 2022
[–]
The point is that it's possible and we're improving on it every day.
Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
