causal

Alignment Must Be Right on the First Try

The core lethality of AI is that you have to get alignment right on the first try or it kills you, and getting something right on the first try without the infinite free retries usually available in science and engineering is an insanely lethal ask; this, not a difference about base rates, is the real disagreement with optimists like Scott Aaronson.

causalpending

Speaker

Eliezer Yudkowsky

Evidence Quote

“you have to get something right on the first try or it kills you”

Source

Eliezer Yudkowsky on the Dangers of AI— EconTalk
Created: 6/13/2026, 12:26:27 AM

Your notes

Loading notes...