Back to feed

AI Alignment Is Impossible, not just in practice but in theory

Matt Lutz at Persuasion: Unfortunately, I’m pretty sure that AI alignment is impossible. How might an AI form a moral sense. There are basically two scenarios.

There are basically two scenarios. In one scenario, moral facts are the kind of fact that one might simply figure out by thinking about them hard. In such a case, perhaps AIs.

In such a case, perhaps AIs.

Continue Reading on 3 Quarks Daily

This article continues with additional insights and analysis. Read the full article for free.

Read Full Article on 3 Quarks Daily