Joe Carlsmith's Substack

Controlling the options AIs can pursue

On blocking paths to power, and on making deals.

Sep 29 • 

Joe Carlsmith

5

Video and transcript of talk on giving AIs safe motivations

From a talk at UT Austin in September 2025.

Sep 22 • 

Joe Carlsmith

3

August 2025

Giving AIs safe motivations

A four-part picture.

Aug 18 • 

Joe Carlsmith

10

1

July 2025

Video and transcript of talk on "Can goodness compete?"

From a public talk on long-term equilibria post-AGI, given at Mox in SF in July 2025.

Jul 17 • 

Joe Carlsmith

15

May 2025

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 • 

Joe Carlsmith

5

1

The stakes of AI moral status

On seeing and not seeing souls.

May 21

31

11

April 2025

Video and transcript of talk on automating alignment research

From a talk at Anthropic in April 2025

Apr 30 • 

Joe Carlsmith

5

1

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 • 

Joe Carlsmith

5

March 2025

AI for AI safety

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

Mar 14 • 

Joe Carlsmith

9

2

Paths and waystations in AI safety

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

Mar 11 • 

Joe Carlsmith

7

1

February 2025

When should we worry about AI power-seeking?

Examining the conditions required for rogue AI behavior.

Feb 19 • 

Joe Carlsmith

3

1

What is it to solve the alignment problem?

Also: to avoid it? Handle it? Solve it forever? Solve it completely?

Feb 13 • 

Joe Carlsmith

16

1