Last updated: 09.29.2022
Published: 09.15.2020
How much computational power does it take to match the human brain?
Further reading
11.12.2025
How do we solve the alignment problem? / Part 9:
How human-like do safe AI motivations need to be?AIs with alien motivations can still follow instructions safely on the inputs that matter.
Continue reading
11.03.2025
Leaving Open Philanthropy, going to Anthropic
On a career move, and on AI-safety-focused people working at AI companies.
Continue reading
09.29.2025
How do we solve the alignment problem? / Part 8:
Controlling the options AIs can pursueOn blocking paths to power, and on making deals.
Continue reading