Lots of
for Stuart, but I never managed to get past the "*whose* benefit/values is the #AI supposed to align with?" qn
Pending someone figuring out a magical way to make humans uniform & nice, there is neither a single human nor a single #AI...https://nyti.ms/2MpvEoJ
-
-
Top-down value alignment never works.
-
The direction from which you align is usually called the top
- 1 more reply
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.