✳flâneur — a map of the web's best reading

Putting up Bumpers

alignment.anthropic.com · 4,848 words · saved by 1 readers

If a child is bowling for the first time, and they just aim at the pins and throw, they’re almost certain to miss. Their ball will fall into one of the gutters. But if there were beginners’ bumpers in place blocking much of the length of those gutters, their throw would be almost certain to hit at least a few pins. This essay describes an alignment strategy for early AGI systems I call ‘putting up bumpers’, in which we treat it as a top priority to implement and test safeguards that allow us to course-correct if we turn out to have built or deployed a misaligned model, in the same way that bowling bumpers allow a poorly aimed ball to reach its target. To do this, we'd aim to build up many largely-independent lines of defense that allow us to catch and respond to early signs of misalignment. This would involve significantly improving and scaling up our use of tools like mechanistic interpretability audits, behavioral red-teaming, and early post-deployment monitoring. We believe that, ev

Putting up Bumpers Alignment Science Blog Putting up Bumpers Image by a4gpa on Flickr (CC BY-SA 2.0) tl;dr Even if we can't solve alignment, we can solve the problem of catching and fixing misalignment. If a child is bowling for the first time, and they just aim at the pins and throw, they’re almost certain to miss. Their ball will fall into one of the gutters. But if there were beginners’ bumpers in place blocking much of the length of those gutters, their throw would be almost certain to hit at least a few pins. This essay describes an alignment strategy for early AGI systems I call ‘putting

Explore this link on the map →

saved by

related reading