[seanhunter]

I agree with you on both points, but they have QA which is 1. The long-term risk team was more of a research/futurology/navel-gazing entity rather than a qa/audit function. I would say if you have any possible safety/alignment test that you can feasibly run it should be part of the CI/CD pipline and be run during training also. That's not what that group was doing.

[doktrin]

That’s quite the narrow goalpost you’ve set up. What happens if a problem can’t be expressed as a Jenkins pipeline operation?