RSS

mariushobbhahn

Karma: 2,592

I recently founded Apollo Research: https://​​www.apolloresearch.ai/​​

I was previously doing a Ph.D. in ML at the International Max-Planck research school in Tübingen, worked part-time with Epoch and did independent AI safety research.

For more see https://​​www.mariushobbhahn.com/​​aboutme/​​

I subscribe to Crocker’s Rules

How to write bet­ter blog posts

mariushobbhahn25 Jan 2022 12:29 UTC
79 points
5 comments6 min readEA link

EA Anal­y­sis of the Ger­man Coal­i­tion Agree­ment 2021–2025

Yannick_Muehlhaeuser24 Jan 2022 13:25 UTC
75 points
16 comments9 min readEA link

AI ac­cel­er­a­tion from a safety per­spec­tive: Trade-offs and con­sid­er­a­tions

mariushobbhahn19 Jan 2022 9:44 UTC
12 points
1 comment7 min readEA link

What is the role of Bayesian ML for AI al­ign­ment/​safety?

mariushobbhahn11 Jan 2022 8:07 UTC
39 points
6 comments3 min readEA link

EA megapro­jects continued

mariushobbhahn3 Dec 2021 10:33 UTC
183 points
48 comments7 min readEA link

When to get off the train to crazy town?

mariushobbhahn22 Nov 2021 7:30 UTC
76 points
13 comments2 min readEA link

[Dis­cus­sion] Best in­tu­ition pumps for AI safety

mariushobbhahn6 Nov 2021 8:11 UTC
10 points
8 comments1 min readEA link

Con­struc­tive Crit­i­cism of Mo­ral Uncer­tainty (book)

mariushobbhahn4 Jun 2021 6:04 UTC
28 points
3 comments5 min readEA link

Should Chronic Pain be a cause area?

mariushobbhahn18 May 2021 11:31 UTC
69 points
12 comments12 min readEA link

Thoughts on Per­sonal Fi­nance for Effec­tive Altruists

mariushobbhahn29 Jan 2021 12:48 UTC
29 points
4 comments14 min readEA link

Ma­chine Learn­ing and Effec­tive Altruism

mariushobbhahn16 Jan 2021 8:46 UTC
11 points
0 comments2 min readEA link

How much (phys­i­cal) suffer­ing is there? Part II: Animals

mariushobbhahn10 Jan 2021 12:48 UTC
13 points
4 comments15 min readEA link

How much (phys­i­cal) suffer­ing is there? Part I: Humans

mariushobbhahn10 Jan 2021 12:47 UTC
10 points
4 comments11 min readEA link