normative

Interest In What Shifts Probability Not Point Estimates

Rather than committing to a probability distribution over whether alignment is trivial, hard-but-solvable, or impossible, Amodei is more interested in what we could learn that shifts probability mass between these scenarios; mechanistic interpretability is valuable primarily because it teaches us what is going on when we try to align models — for example revealing whether problems get moved around rather than stamped out.

normativepending

Speaker

Dario Amodei (Anthropic CEO)

Evidence Quote

“I have a substantial probability mass on — this all goes wrong, it's a complete disaster, but in a completely different way than anyone had anticipated it would.”

Source

Dario Amodei (Anthropic CEO) — The hidden pattern behind every AI breakthrough— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:25:28 AM

Your notes

Loading notes...