NicholasKross

[SEE NEW EDITS] No, *You* Need to Write Clearer

A Quick List of Some Prob­lems in AI Align­ment As A Field

Quick Thoughts on A.I. Governance

Align­ment Me­gapro­jects: You’re Not Even Try­ing to Have Ideas

[Question] In­tel­li­gence En­hance­ment (Monthly Thread) 13 Oct 2023

Dreams of “Matho­pe­dia”

Why I’m Not (Yet) A Full-Time Tech­ni­cal Align­ment Researcher

• NicholasKross 14 Mar 2023 23:38 UTC

  39 points

  40

  on: Shut­ting Down the Light­cone Offices

  Extremely strong upvote for Oliver’s 2nd message.

  Also, not as related: kudos for actually materially changing the course of your organization, something which is hard for most organizations, period.

Learn­ing Math in Time for Alignment

There Meat Come A Scan­dal...

• NicholasKross 28 Dec 2021 23:22 UTC

  30 points

  on: A non-mag­i­cal ex­pla­na­tion of Jeffrey Epstein

  This is pretty good, although you ought to actually link more of the citations for specific facts. Court documents, testimonies, company docs, even Wikipedia would’ve been helpful for the part about IAG.

[Question] In­cen­tives af­fect­ing al­ign­ment-re­searcher encouragement

[Question] Ways to in­crease work­ing mem­ory, and/​or cope with low work­ing mem­ory?

[Question] Ways to be more agenty?

[Question] Burst work or steady work?

I am a Me­moryless System

Don’t Look Up (Film Re­view)

My AI Align­ment Re­search Agenda and Threat Model, right now (May 2023)

• NicholasKross 26 May 2022 22:28 UTC

  25 points

  on: Right now, you’re sit­ting on a REDONKULOUS op­por­tu­nity to help solve AGI (and rake in $$$)

  (Semi-dumb LW category suggestion: Posts That Could Have Made You Good Money In Hindsight)

My Align­ment Timeline