I am an independent AI safety researcher based at the Monastic Academy in Vermont. My work concerns foundational theories of knowledge, optimization, and agency. Here are some links to recent work:

• Implications of automated ontology identification
• Alignment versus AI alignment
• The ground of optimization
• Search versus design

Here are some links to shorter pieces:

• Agency in Conway's game of life
• Our take on CHAI's research agenda

You may support me by making a monthly donation using one of the buttons below. To make a one-off donation, please contact me at alex.flint@gmail.com.

$4 per month $20 per month $100 per month $500 per month