alt Hacker NewsBefore AGI can choose for itself, it will depend on its creators to decide what it values and how it behaves. We can see how that works whenever grok gets the answer factual.
Replies
Andrex • yesterday at 11:53 PM
Am I the only one seeing the very obvious parallels to child rearing here...
➕ show 2 replies
fragmede • yesterday at 8:18 PM
Elon's basilisk
Very likely humans wont actually understand how the thing we designed works other than in some hand-wavvy statistical way. It'll be a race to whatever works first. There won't be some intentional intelligent design.