Questions tagged [ai-safety]

For questions regarding various parameters/methods of implementation/improvement/analyzing the safety of an Artificially Intelligent algorithm. A typical real world example is autonomous vehicles.

3 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
2
votes
0answers
74 views

Does Rice's theorem prove safe AI is undecidable?

According to Wikipedia In computability theory, Rice's theorem states that all non-trivial, semantic properties of programs are undecidable. A semantic property is one about the program's ...
1
vote
0answers
22 views

To what level of abstraction must fully automated vehicles build their driving model before safety can be maximized?

There are several levels of abstraction involved in piloting and driving. Signals representing the state of the vehicle and its environment originating from multiple transducers1 Latched sample ...
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 ...