“Minimum required pacing: finish aligning it before you train the next one” by orthonormal

LessWrong (30+ Karma) · Oct 11, 2026 · 4m

Let's say we coordinate to pace the frontier, but we don't coordinate on an outright pause. What should the standard of pacing be?

My proposal for a minimum requirement: a lab cannot train the next generation of models (in terms of capabilities) until they have adequately resolved all significant alignment issues in the present generation of models.

You don't launch a jet that goes at Mach 3 before you've figured out why your Mach 2 jet keeps crashing. With any other kind of dangerous technology, we wouldn't accept "shrug and move on".

This proposal may appeal to many prosaic-alignment…