Gabriel Alfour

• Gabriel AlfourApr 14, 2025, 12:05 PM

  2 points

  0

  on: Why does LW not put much more fo­cus on AI gov­er­nance and out­reach?

  Happy to have a public conversation on the topic. Just DM me on Twitter if you are interested.

Ide­olo­gies are slow and nec­es­sary, for now

Con­jec­ture: A Roadmap for Cog­ni­tive Soft­ware and A Hu­man­ist Fu­ture of AI

The Com­pendium, A full ar­gu­ment about ex­tinc­tion risk from AGI

“Epistemic range of mo­tion” and LessWrong moderation

There is no IQ for AI

For Civ­i­liza­tion and Against Niceness

On Lies and Liars

• Gabriel AlfourOct 24, 2023, 3:22 PM

  5 points

  2

  in reply to: Joe Collman’s comment on: Ly­ing is Cowardice, not Strategy

  By this logic, any instrumental action taken towards an altruistic goal would be “for personal gain”.

  I think you are making a genuine mistake, and that I could have been clearer.

  There are instrumental actions that favour everyone (raising epistemic standards), and instrumental actions that favour you (making money).

  The latter are for personal gains, regardless of your end goals.

  Sorry for not getting deeper into it in this comment. This is quite a vast topic.
  I might instead write a longer post about the interactions of deontology & consequentialism, and egoism & altruism.

Ly­ing is Cowardice, not Strategy

Cog­ni­tive Emu­la­tion: A Naive AI Safety Proposal

Chris­ti­ano (ARC) and GA (Con­jec­ture) Dis­cuss Align­ment Cruxes

• Gabriel AlfourFeb 19, 2023, 9:57 AM

  8 points

  4

  in reply to: cfoster0’s comment on: AGI in sight: our look at the game board

  (I strongly upvoted the comment to signal boost it, and possibly let people who agree easily express their agreement to it directly if they don’t have any specific meta-level observation to share)

  What links here?

  • My guess at Con­jec­ture’s vi­sion: trig­ger­ing a nar­ra­tive bifurcation by Alexandre Variengien (Feb 6, 2024, 7:10 PM; 75 points)

AGI in sight: our look at the game board

Hu­man de­ci­sion pro­cesses are not well factored

As­sign­ing Praise and Blame: De­cou­pling Episte­mol­ogy and De­ci­sion Theory

Group-level Con­se­quences of Psy­cholog­i­cal Problems

Reifi­ca­tion bias

Men­tal ac­cep­tance and reflection

Psy­cholog­i­cal Di­sor­ders and Problems