paulfchristiano comments on Common misconceptions about OpenAI

[paulfchristiano]

I was replying to:

I’d guess that is an overestimate of the number of people actually doing alignment research at OpenAI, as opposed to capabilities research in which people pay lip service to alignment. In particular, all of the RLHF work is basically capabilities work which makes alignment harder in the long term (because it directly selects for deception), while billing itself as “alignment”.

[Steven Byrnes]

Thanks, sorry for misunderstanding.