Software Engineer in Test @ Solu/Paychex



Software engineer, blogging and editing at /nickai/. PM me your fluid-g-increasing ideas. (Formerly President/VP of the EA Club at RIT (NY, USA)).

How others can help me

Looking for opportunities to do technical and/or governance work in AI alignment/safety.

How I can help others

Can help with some level of technical analysis (and I'm improving!), strategic planning, operations management, social media marketing, graphic design.


TIL that a field called "argumentation theory" exists, thanks!

Reading this quickly on my lunch break, seems accurate to most of my core points. Not how I'd phrase them, but maybe that's to be expected(?)

Agreed. IMHO the only legitimate reason to make a list like this, is to prep for researching and writing one or more response pieces.

(There's a question of who would actually read those responses, and correspondingly where they'd be published, but that's a key question that all persuasive-media-creators should be answering anyway.)

Yeah I get that, I mean specifically the weird risky hardcore projects. (Hence specifying "adult", since that's both harder and potentially more necessary under e.g. short/medium AI timelines.)

Is any EA group funding adult human intelligence augmentation? It seems broadly useful for lots of cause areas, especially research-bottlenecked ones like AI alignment.

Why hasn't e.g. OpenPhil funded this project?: https://www.lesswrong.com/posts/JEhW3HDMKzekDShva/significantly-enhancing-adult-intelligence-with-gene-editing

There's a new chart template that is better than "P(doom)" for most people.

Have long hoped someone would do this thoroughly, thank you.

Much cheaper, though still hokey, ideas that you should have already thought of at some point:

  • A "formalization office" that checks and formalizes results by alignment researchers. It should not take months for a John Wentworth result to get formalized by someone else.
  • Mathopedia.
  • Alignment-specific outreach at campuses/conventions with top cybersecurity people.

Maybe! I'm most interested in math because of its utility for AI alignment and because math (especially advanced math) is notoriously considered "hard" or "impenetrable" by many people (even people who otherwise consider themselves smart/competent). Part of that is probably lack of good math-intuitions (grokking-by-playing-with-concept, maths-is-about-abstract-objects, law-thinking, etc.).

Yeah, we'd hope there's a good bit of existing pedagogy that applies to this. Not much stood out to me, but maybe I haven't looked hard enough at the field.

Load more