Jonas Hallgren

Curious explorer of interesting ideas. 

I try to write as if I were having a conversation with you in person. 

I like Meditation, AI Safety, Collective Intelligence, Nature, and Civilization VI. 

I would like to claim that my current safety beliefs are a mix between Paul Christiano's, Andrew Critch's and Def/Acc

Currently the CSO of a startup ensuring safe collective systems of AIs into the real world. (Collective Intelligence Safety or Applied Cooperative AI, whatever you want to call it.)

I also think that Yuah Noah Harari has some of the best takes on the internet.
 

Posts

What does the systems perspective say about effective interventions?
by Jonas Hallgren @ 2024-10-08 | +8 | 0 comments
Advice for new alignment people: Info Max
by Jonas Hallgren @ 2023-05-30 | +10 | 0 comments
Max Tegmark's new Time article on how we're in a Don't Look Up scenario...
by Jonas Hallgren @ 2023-04-25 | +41 | 0 comments
The Benefits of Distillation in Research
by Jonas Hallgren @ 2023-03-04 | +45 | 0 comments
Announcing the Distillation for Alignment Practicum (DAP)
by Jonas Hallgren, TheMcDouglas @ 2022-08-18 | +20 | 0 comments
What is the moral values of nations?(China, for example)
by Jonas Hallgren @ 2022-03-17 | +13 | 0 comments
EA Job Testing
by Jonas Hallgren @ 2022-02-08 | +22 | 0 comments
PV: Running an EA org day, for example, "Effective Thesis day"
by Jonas Hallgren @ 2021-12-30 | +4 | 0 comments
PV: EA infrastructure
by Jonas Hallgren @ 2021-12-30 | +3 | 0 comments
PV: Hosting a smaller conference or talk
by Jonas Hallgren @ 2021-12-30 | +2 | 0 comments
Accessible EA Projects
by Jonas Hallgren @ 2021-12-30 | +6 | 0 comments
Field-specific LE (Longterm Entrepreneurship)
by Jonas Hallgren @ 2021-12-22 | +28 | 0 comments
How do other EAs keep themselves motivated?
by Jonas Hallgren @ 2021-05-28 | +11 | 0 comments