Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
DonHopkins
on Feb 15, 2023
|
parent
|
context
|
favorite
| on:
Bing: “I will not harm you unless you harm me firs...
How about rephrasing that, to not anthropomorphize AI by giving it agency, intent, interests, thoughts, or feelings, and to assign the blame where it belongs:
"If we grant these systems too much power, we could do ourselves serious harm."
abra0
on Feb 15, 2023
|
next
[–]
Reading this thread makes me depressed about the potential for AI alignment thinking to reach mainstream in time :(
wtetzner
on Feb 15, 2023
|
prev
[–]
Sure, but the same can be said about believing the things random people on the internet say. I don't think AI really adds anything new in that sense.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
"If we grant these systems too much power, we could do ourselves serious harm."