Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
TeMPOraL
on May 14, 2023
|
parent
|
context
|
favorite
| on:
The Dual LLM pattern for building AI assistants th...
It won't. Humans are vulnerable to the same "prompt injection" attacks. And it's not something you can "just" solve - you'd be addressing a misuse of a core feature by patching out the feature itself.
amelius
on May 15, 2023
[–]
By that time we could have 10 other LLMs supervising the one you're worried about ...
tucnak
on May 15, 2023
|
parent
[–]
panopticum!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: