New Year resolution

[dmm]

To read my https://twitter.com/home more regularly (that's absolutely the best source of info at the moment).

A small fraction of today's catch:

New work by Janus

A new involved take on AI safety/alignment

(What's the right way to organize all that information?)

Links are in the comments (I think the new work by Janus is more important even for alignment, and is just overall more important of the two topics of this post)...

Comments

[dmm]

Further things related to Janus ("repligate"):

https://liberaugmen.com/

via https://twitter.com/jd_pressman/status/1612106688122990592

"Basically everything in Liber Augmen is between 1024 and 2048 characters and it's pretty much nonstop expression of complex ideas. Does it suffer for that sometimes? Yeah, but not as much as you'd think."

and https://twitter.com/repligate/status/1612167786930864128

"Liber Augmen is a masterpiece of compressed insight and the only good work of this genre I've seen since the Sequences. Read it, you fools."

[dmm]

https://www.lesswrong.com/posts/cTdAXCb7WK6eR4fxf/what-specific-thing-would-you-do-with-ai-alignment-research

https://www.lesswrong.com/posts/a2io2mcxTWS4mxodF/results-from-a-survey-on-tool-use-and-workflows-in-alignment