azsantosk

Karma: 222

Co-founder and CEO of quiver.trade. Interested in mechanism design and neuroscience. Hopes to contribute to AI alignment.

Twitter: https://twitter.com/azsantosk

[Question] Does AI governance needs a “Federalist papers” debate?

azsantosk18 Oct 2023 21:08 UTC

40 points

4 comments1 min readLW link

Contra Kevin Dorst’s Rational Polarization

azsantosk22 Sep 2023 4:28 UTC

8 points

2 comments9 min readLW link

Optimization happens inside the mind, not in the world

azsantosk3 Jun 2023 21:36 UTC

17 points

10 comments5 min readLW link

I bet $500 on AI winning the IMO gold medal by 2026

azsantosk11 May 2023 14:46 UTC

37 points

27 comments1 min readLW link

Cruxes in Katja Grace’s Counterarguments

azsantosk16 Oct 2022 8:44 UTC

16 points

0 comments7 min readLW link

Pivotal acts from Math AIs

azsantosk15 Apr 2022 0:25 UTC

10 points

4 comments5 min readLW link

An AI-in-a-box success model

azsantosk11 Apr 2022 22:28 UTC

16 points

1 comment10 min readLW link

Reverse (intent) alignment may allow for safer Oracles

azsantosk8 Apr 2022 2:48 UTC

4 points

0 comments4 min readLW link

Strategies for differential divulgation of key ideas in AI capability

azsantosk29 Mar 2022 3:22 UTC

8 points

0 comments6 min readLW link

We cannot directly choose an AGI’s utility function

azsantosk21 Mar 2022 22:08 UTC

12 points

18 comments3 min readLW link

Why will an AGI be rational?

azsantosk21 Mar 2022 21:54 UTC

4 points

8 comments2 min readLW link