x

AI ALIGNMENT FORUM

AF

annawang

annawang

Message

https://annaywang.com/

11

Ω

10

1

2d

annawang

https://annaywang.com/

annawang — AI Alignment Forum

Delaying Internal Deployments Until After X Days of Safety Testing

This post reflects my own takes, and not that of my employer's. This is a simple idea: before a new model can be deployed internally, you must first test it for a minimum, fixed period. You can adjust various axes of this proposal: 1. Duration of the wait: in calendar...