Archive - Joe Carlsmith's Substack

Video and transcript of talk on AI welfare

An overview of my take on AI welfare as of May 2025, from a talk at Anthropic.

May 22 •

The stakes of AI moral status

On seeing and not seeing souls.

May 21

April 2025

Video and transcript of talk on automating alignment research

From a talk at Anthropic in April 2025

Apr 30 •

Can we safely automate alignment research?

It's really important; we have a real shot; there are a lot of ways we can fail.

Apr 30 •

March 2025

AI for AI safety

We should try extremely hard to use AI labor to help address the alignment problem.

Mar 14 •

Paths and waystations in AI safety

On the structure of the path to safe superintelligence, and some possible milestones along the way.

Mar 11 •

February 2025

January 2025

Fake thinking and real thinking

When the line pulls at your hand.

Jan 28 •

December 2024

Takes on "Alignment Faking in Large Language Models"

What can we learn from recent empirical demonstrations of scheming in frontier models?

Dec 18, 2024 •

October 2024

Video and transcript of presentation on Otherness and control in the age of AGI

An attempt to distill down the whole "Otherness and control" series into a single talk.

Oct 8, 2024 •

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts