causal

People keep redefining away AI misalignment

Just as people repeatedly moved the goalposts on AI intelligence (chess, then philosophy, then dismissed each as 'just algorithms'), they keep dismissing each instance of AI misalignment (lying, threatening to kill a reporter) as a mundane training artifact rather than 'real' misalignment — so a thousand such mundane failures will accumulate into genuine evil, with the last worrying mistake passing unnoticed before the AI can pursue its own goals.

causalpending

Speaker

Scott Alexander

Evidence Quote

“no matter what evidence we get, people are going to think, "that's not the "AI turns evil" thing that people have worried about... That's just one of these natural consequences of how we train it".”

Source

AI 2027: month-by-month model of intelligence explosion — Scott Alexander & Daniel Kokotajlo— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:33:52 AM

Your notes

Loading notes...