normative

Publish A Model's Desired Behavior Spec

To handle bias and safety disputes, companies should write out the desired behavior of a model—concretely specifying how it should respond to specific prompts, including edge cases—make it public, and take input on it, so that when a model misbehaves it is clear whether that is a bug to fix or intended behavior to debate at the policy level, rather than being caught ambiguously in between.

normativepending

Speaker

Sam Altman

Evidence Quote

when a model is not behaving in a way that you want, it’s at least clear about whether that’s a bug the company should fix or behaving as intended and you should debate the policy.

Source

Sam Altman #2Lex Fridman Podcast
Created: 6/13/2026, 3:36:04 AM

My Notes

Loading notes...