Our readingWhat is a korrent?
Once models start getting capable of takeover, labs should not be allowed to make them more powerful until they have much better arguments and tests that it is safe.
Drawn from what Ajeya Cotra said
SubjectAI alignment
Our readingWhat is a korrent?
Drawn from what Ajeya Cotra said
As soon as that starts to change, you want some alarm bells to go off, and you want the AI labs to not be allowed to make the models any more powerful until they have a much better argument and set of tests that it’s actually safe.
Where this was said
↗Ajeya Cotra on accidentally teaching AI models to deceive us (80,000 Hours)80000hours.org
All 24 korrents from this piecethis one is 16th
Added to korrents 8 Nov 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.