Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
saurik
49 days ago
|
parent
|
context
|
favorite
| on:
Language models are injective and hence invertible
The input isn't the training data, the input is the prompt.
spuz
49 days ago
[–]
Ah ok, for some reason that wasn't clear for me.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: