Joe Carlsmith
  • About
  • Archive
How much computational power does it take to match the human brain?
Last updated: 09.29.2022
Published: 09.15.2020

How much computational power does it take to match the human brain?

Further reading

01.29.2026
How do we solve the alignment problem? / Part 10:
Building AIs that do human-like philosophy

AIs will face philosophical questions humans can’t answer for them.

Continue reading
12.17.2025
Video and transcript of talk on human-like-ness in AI safety

From a talk I gave at Constellation in December 2025.

Continue 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
@ Joe Carlsmith, 2026
  • Policies
Designed by And–Now