Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
simonw
85 days ago
|
parent
|
context
|
favorite
| on:
How to stop AI's "lethal trifecta"
I don't like any of the solutions that propose guardrails or filters to detect and block potential attacks. I think they're making promises that they can't keep, and encouraging people to ship products that are inherently insecure.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: