Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
mathgorges
on Oct 19, 2023
|
parent
|
context
|
favorite
| on:
GPT-4 vision prompt injection
Thus separating the model’s logic from the model’s data.
All that was old is new again :) [0]
0: s/model/program/
bytefactory
on Oct 19, 2023
[–]
It's interesting how this is not presumably the case within the weights of the LLM itself. Those probably encode data as well as logic!
Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
All that was old is new again :) [0]
0: s/model/program/