Video and transcript of talk on writing AI constitutions
From a talk at Yale Law School in March 2026.
Joseph Carlsmith RSS Feed
Joseph Carlsmith's Personal Website
Latest posts
On restraining AI development for the sake of safety
My take on slowing down AI.
Building AIs that do human-like philosophy
AIs will face philosophical questions humans can t answer for them.
Video and transcript of talk on human-like-ness in AI safety
From a talk I gave at Constellation in December 2025.
How human-like do safe AI motivations need to be?
AIs with alien motivations can still follow instructions safely on the inputs that matter.
Leaving Open Philanthropy, going to Anthropic
On a career move, and on AI-safety-focused people working at AI companies.
Controlling the options AIs can pursue
On blocking paths to power, and on making deals.
Video and transcript of talk on giving AIs safe motivations
From a talk at UT Austin in September 2025.
Giving AIs safe motivations
A four-part picture.
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.
Video and transcript of talk on AI welfare
An overview of my take on AI welfare as of May 2025, from a talk I gave at Anthropic.
The stakes of AI moral status
On seeing and not seeing souls.
Video and transcript of talk on automating alignment research
From a talk at Anthropic in April 2025.
Can we safely automate alignment research?
It s really important; we have a real shot; there are a lot of ways we can fail.
AI for AI safety
We should try extremely hard to use AI labor to help address the alignment problem.
Paths and waystations in AI safety
On the structure of the path to safe superintelligence, and some possible milestones along the way.
When should we worry about AI power-seeking?
Examining the conditions for rogue AI behavior.
How do we solve the alignment problem?
Introduction to an essay series about paths to safe, useful superintelligence.
What is it to solve the alignment problem?
Also: to avoid it? Handle it? Solve it forever? Solve it completely?
Fake thinking and real thinking
When the line pulls at your hand.
Takes on “Alignment Faking in Large Language Models”
What can we learn from recent empirical demonstrations of scheming in frontier models?
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.
(Part 2, AI takeover) Extended audio/transcript from my conversation with Dwarkesh Patel
Extra content includes: AI collusion; the nature of intelligence; concrete takeover scenarios; flawed training signals; tribalism and mistake theory; more on what good outcomes look like.
(Part 1, Otherness) Extended audio/transcript from my conversation with Dwarkesh Patel
Extra content includes: regretting alignment; predictable updating; dealing with potentially game-changing uncertainties; intersections between meditation and AI alignment; moral patienthood without consciousness; p(God).
Loving a world you don’t trust
Garden, campfire, healing water.
On attunement
Examining a certain kind of meaning-laden receptivity to the world.
Video and transcript of presentation on Scheming AIs
An intro to my work on scheming/ deceptive alignment.
On green
Examining a philosophical vibe that I think contrasts in interesting ways with deep atheism.
On the abolition of man
What does it take to avoid tyranny towards the future?
Being nicer than Clippy
Let s be the sort of species that aliens wouldn’t fear the way we fear paperclippers.
An even deeper atheism
Who isn t a paperclipper?
Does AI risk “other” the AIs?
Examining Robin Hanson s critique of the AI risk discourse.
When “yang” goes wrong
On the connection between deep atheism and seeking control.
Deep atheism and AI risk
On a certain kind of fundamental mistrust towards Nature.
Gentleness and the artificial Other
AIs as fellow creatures. And on getting eaten.
Otherness and control in the age of AGI
Introduction and summary for a series of essays about how agents with different values should relate to one another, and about the ethics of seeking and sharing power.
New report: “Scheming AIs: Will AIs fake alignment during training in order to get power?”
My report examining the probability of a behavior often called deceptive alignment.
Superforecasting the premises in “Is power-seeking AI an existential risk?”
Superforecasters weigh in on the argument for AI risk given in my report on the topic.
In memory of Louise Glück
It was, she said, a great discovery, albeit my real life.
Predictable updating about AI risk
How worried about AI risk will we be when we can see advanced machine intelligence up close? We should worry accordingly now.
Existential Risk from Power-Seeking AI (shorter version)
Building a second advanced species is playing with fire.
A Stranger Priority? Topics at the Outer Reaches of Effective Altruism
My dissertation.
Seeing more whole
On looking out of your own eyes.
Why should ethical anti-realists do ethics?
Who needs a system if you re free?
On sincerity
Nearby is the country they call life.
Against meta-ethical hedonism
Can the epistemology of consciousness save moral realism and redeem experience machines? No.
Against the normative realist’s wager
If you find a button that gives you a hundred dollars if a certain controversial meta-ethical view is true, but you and your family get burned alive if that view is false, should you press the button? No.
Is Power-Seeking AI an Existential Risk?
Report for Open Philanthropy examining what I see as the core argument for concern about existential risk from misaligned artificial intelligence.
Video and Transcript of Presentation on Existential Risk from Power-Seeking AI
Video and transcript of a presentation I gave on existential risk from power-seeking AI, summarizing my report on the topic.
Dutch books, Cox, and Complete Class
Final essay in a four-part series on expected utility maximization (EUM). Examination of some theorems that aim to justify the subjective probability aspect of expected utility maximization (EUM), namely: Dutch Book theorems; Cox’s Theorem; and the Complete Class Theorem.