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 PodcastCreated: 6/13/2026, 3:25:28 AM
Your notes
Loading notes...