Source Alignment Forum · Published · Open the original ↗
Lab notes
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: Duration of the wait: in calendar time, or until you fulfill some condition. What it blocks: external deployment, internal deployment, or the training of future checkpoints. When the fixed period starts: from the first checkpoint, the final checkpoint, or any checkpoint that is “sufficiently similar / representative”…
This is a simple idea: before a new model can be deployed internally, you must first test it for a minimum, fixed period.
One concrete target that I like is: “No checkpoint may be used internally for purposes beyond safety testing, until at least X calendar days after its hash is filed with an auditor.”
The opening of the post, quoted unchanged from Alignment Forum. The full text continues at the source.