Mark Xu comments on What is an example of recent, tangible progress in AI safety research?

[Mark Xu]

nit: link on “reasons” was pasted twice. For others it’s https://​​www.lesswrong.com/​​posts/​​PZtsoaoSLpKjjbMqM/​​the-case-for-aligning-narrowly-superhuman-models

Also hadn’t seen that paper. Thanks!