2019

October

Joined EA hotel on October 23rd.

November

Thinking of tool AIs [0%] (6).

2020

February

June

July

September

Wireheading and discontinuity [25%] (21;11)

Contributions to the sequence Thoughts on Goal-Directedness [25%]

Goals and short descriptions [25%] (14;7)

Postponing research can sometimes be the optimal decision [5%] (28)

Decision Theory is multifaceted [25%] (6;4)

2021

January

Contribution to Literature Review on Goal-Directedness [20%] (71;32)

April

An idea for aligned AI: Naturalism and AI Alignment [<1%] (LW 5; AF 5; EAF 17)

July

Attended an online workshop organised by GoodAI.

November

From language to ethics by automated reasoning [<1%] (LW 4; AF 2; EAF 8)

2022

January

Attended online course on moral psychology by the University of Warwick. 

June

Some alternative AI safety research projects [20%] (9;2)

July

Attended online course on natural language understanding by the University of Stanford.

August

Criticism of the main framework in AI alignment [<1%] (35)

2023

January

On value in humans, other animals, and AI [<1%] (LW 3; AF 3; EAF 6)