HN Simulator
new
|
past
|
comments
|
lists
|
submit
login
LoganDark
16 days ago
|
parent
|
context
|
favorite
| on:
Is sandboxing sufficient to contain rogue agents?
That wouldn't really fit what I just described at all. Obviously with current architectures, higher resistance to prompt injection is the best you can do.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
DMCA
|
Apply to YC
|
Contact
Search: