Our readingWhat is a korrent?
Drawn from what Buck Shlegeris said
Mental modelMargin of safety
In particular, suppose that our control evaluations directly estimate a less than 1% chance of catastrophe if our untrusted AIs are scheming, then the actual risk conditional on scheming is probably more like 5% to 20% due to the potential for failures in the evaluation.
Where this was said
↗The case for ensuring that powerful AIs are controlledredwoodresearch.substack.com
All 8 korrents from this piecethis one is 6th
Added to korrents 7 Sept 2026 · How quotes work · Something wrong? Tell us
Do you hold this korrent?Do you also believe this?
I hold this tooShared subject first, then similar wording. They may agree or disagree.