Karma: 3,302

Studying behaviour and interactions of boundedly rational agents, AI alignment and complex systems.

Research fellow at Future of Humanity Institute, Oxford. Other projects: European Summer Program on Rationality. Human-aligned AI Summer School. Epistea Lab.

Deon­tol­ogy and virtue ethics as “effec­tive the­o­ries” of con­se­quen­tial­ist ethics

Jan_Kulveit17 Nov 2022 9:20 UTC
47 points
11 comments10 min readEA link

We can do bet­ter than argmax

Jan_Kulveit10 Oct 2022 10:32 UTC
111 points
37 comments10 min readEA link

Limits to Legibility

Jan_Kulveit29 Jun 2022 17:45 UTC
98 points
3 comments5 min readEA link