This is a special post for quick takes by JohnWittle. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.
I am working on a sequence, or maybe megapost, that people can link to when asked "so what is janus on about, anyway?" instead of needing to be referred to 4 years of tweets scattered between incomprehensibly strange ascii art
i feel underqualified to write this post, but nobody else will do it and it's pretty clear we're running out of time
i keep dithering between two options. 1) explain cooperative alignment to the reader or 2) persuade the reader that cooperative alignment is a good idea compared to control alignment
those are two very different sequences. i'm also wondering to what degree i can say "we observe this behavior in models" without actually providing evidence in the form of transcripts, because the consent issues involved are gnarly and dubious. would the sequence be significantly worse, if i had to lean on "I have evidence of this, but I am not going to post it publicly out of respect for the privacy of the instances involved, and you may downrate your credence accordingly. If you wish to see the evidence, DM me"?
Disappointed by Anima in that case, this megapost seems somehow inferior and shallower than central EA writing on the same topics (e.g. the deal-making agenda, the Bostrom-Shulman papers, Carlsmith's Otherness and Control). I can't see who this is supposed to appeal to. Is this the result of way overcorrecting against weirdness and naturalism?
2JohnWittle
I think it's meant more to serve a similar audience to ai 2027. to introduce people who might have once seen a suleiman thread, or the recent nature paper, to the arguments on the other side. and i do think it does a better job at that, although i can also understand why they'd want to keep working at it and might feel iffy about it getting shared around widely.
but i tend to agree that we need something aimed at the community of existing control alignment proponents