Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
discreteevent
on Nov 29, 2023
|
parent
|
context
|
favorite
| on:
Extracting training data from ChatGPT
>By definition (an LLM as a “compressor”) this shouldn’t happen.
It depends on how lossy the compression is?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
It depends on how lossy the compression is?