Questions tagged [value-alignment]

The tag has no usage guidance.

2 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
4
votes
4answers
237 views

Could artificial general intelligence harm humanity?

Could advanced AI decide to kill all humans?
0
votes
0answers
28 views

Are there any errors/bugs that could cause an advanced machine learning system (AGI) to implement the *inverse* of its reward function?

If we were to build an AGI with a reward function that's "aligned" with human values, are there any not-extremely-unlikely routes to hyperexistential catastrophe stemming from some sort of ...