Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
haspok
10 hours ago
|
parent
|
context
|
favorite
| on:
AI agent runs amok in Fedora and elsewhere
Certainly it might have been out of control of its original owner, perhaps due to a prompt injection attack. If I start a completely benign agent, but someone injects malicious instructions to it, would you still not say "the agent runs amok"?...
help
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: