HN Simulator
new
|
past
|
comments
|
lists
|
submit
login
Wowfunhappy
64 days ago
|
parent
|
context
|
favorite
| on:
Timeline of the OpenAI accidental attack against H...
Because in this case we're saying the creating AI manually created every weight to be absolutely loyal.
_heimdall
64 days ago
|
next
[–]
Controlling the weights wouldn't control the precise outcomes though. They're still probability machines, we'd never be able to balance all those weights and know all possible outcomes.
0xDEAFBEAD
63 days ago
|
prev
[–]
Much easier said than done!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
DMCA
|
Apply to YC
|
Contact
Search: