Joe Carlsmith's Substack
Subscribe
Sign in
Home
My website
Archive
About
58:45
Video and transcript of talk on human-like-ness in AI safety
From a talk at Constellation in December 2025.
Dec 17, 2025
•
Joe Carlsmith
6
1
Latest
Top
Discussions
How human-like do safe AI motivations need to be?
AIs with alien motivations can still follow instructions safely on the inputs that matter.
Nov 12, 2025
•
Joe Carlsmith
7
2
Leaving Open Philanthropy, going to Anthropic
On a career move, and on AI-safety-focused people working at AI companies.
Nov 3, 2025
•
Joe Carlsmith
40
3
3
Controlling the options AIs can pursue
On blocking paths to power, and on making deals.
Sep 29, 2025
•
Joe Carlsmith
5
Video and transcript of talk on giving AIs safe motivations
From a talk at UT Austin in September 2025.
Sep 22, 2025
•
Joe Carlsmith
3
Giving AIs safe motivations
A four-part picture.
Aug 18, 2025
•
Joe Carlsmith
10
1
1
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, 2025
•
Joe Carlsmith
22
6
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, 2025
•
Joe Carlsmith
5
1
See all
Joe Carlsmith's Substack
Philosophy, futurism, and other topics
Subscribe
Recommendations
Sasha's 'Newsletter'
Sasha Chapin
Astral Codex Ten
Scott Alexander
Good Thoughts
Richard Y Chappell
world spirit sock stack
Katja Grace
Also Recommended
Cold Takes
Minding Our Way
Joe Carlsmith's Substack
Subscribe
About
Archive
Recommendations
Sitemap
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
