normative
Dangerous Capability Testing Via Extrapolation
To avoid a 'one-shot' takeover risk when testing whether a powerful model is dangerous, Anthropic plans to set capability thresholds well below dangerous levels — testing for prerequisites to survival in the wild like opening an AWS account and making money for itself — and proceed with more rigorous, careful tests as capabilities increase, extrapolating with factors of two of compute.
normativepending
Speaker
Dario Amodei (Anthropic CEO)Evidence Quote
“what you want to do is you want to extrapolate. We've talked with Arc about this. You have factors of two of compute”
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...