Comment by Marius Hobbhahn

Fundamentally, we just do not know how to do alignment. If somebody came with a thousand-page document that explained exactly how to do everything, we couldn’t get a model to learn exactly that.

Require independent embedded evaluations to close the internal deployment gap. Qualified independent third parties should test models throughout development and internal use, with employee-equivalent access.

The current regime is definitely not optimal. While third-party evaluators try hard to be unbiased, a lab can decide to stop working with them any day for any reason whatsoever. We really need more stringent regulations to improve the incentives for ...