Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
layer8
on March 20, 2023
|
parent
|
context
|
favorite
| on:
Anti-recruiter prompt injection attack in LinkedIn...
You can explain quoting syntax to ChatGPT, and it seems to understand data formats like JSON, so I assume that that should work.
actually_a_dog
on March 20, 2023
|
next
[–]
Yeah. This makes perfect sense if you consider it to be an interpreter for natural language that has a really good macro facility.
nextaccountic
on March 20, 2023
|
prev
[–]
If you do the quoting inside a ChatGPT prompt then it will itself be hijacked with prompt injection
Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
