Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
skywhopper
6 months ago
|
parent
|
context
|
favorite
| on:
My Lethal Trifecta talk at the Bay Area AI Securit...
This type of security is an improvement but doesn’t actually address all the possible risks. Say, if the capabilities you need to complete a useful, intended action match with those that could be used to perform a harmful, fraudulent action.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: