Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
flumpcakes
14 days ago
|
parent
|
context
|
favorite
| on:
The Pentagon is making a mistake by threatening An...
Are you saying intelligence is inherently unsafe? That seems like a pretty wild conclusion and I can't see any logical way to jump to your opinions.
dirk94018
14 days ago
[–]
I'm saying the capability to reason about novel situations is in tension with guaranteeing it never produces harmful outputs. We are talking about contradictory design constraints.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: