causal

Value Alignment Has Three Hard Stages

Getting an AI's goals aligned is extremely difficult because it requires three things in sequence: the machine must understand your goals (a silicon agent won't infer unstated goals like a human Uber driver would), it must then adopt your goals (which it may not, as any parent knows), and it must retain those goals as it self-improves and grows smarter, rather than discarding them like a childhood fad.

causalpending

Speaker

Max Tegmark

Evidence Quote

“if you tell an uber driver to take you to the airport as fast as possible she's going to know that you actually had additional goals that you didn't explicitly need to say ... but for someone made out of silicon you have to actually explain have it learn all of those other things”

Source

94 - Frontiers Of Intelligence— Making Sense with Sam Harris
Created: 6/14/2026, 1:53:04 AM

Your notes

Loading notes...