
ai & services @insightpartners. prev @harvard.
New York, NY
Joined December 2012
- Tweets2.7K
- Following7.1K
- Followers1.2K
- Likes39.2K
alex debayo-doherty retweeted
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had
with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works
already-clean.goodfire.com/
alex debayo-doherty retweeted
Terence Tao just posted this really insightful thread which seems to have been written in reaction to the Navier Stokes announcement. Please give it a read. mathstodon.xyz/@tao/11723732…
We’re sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics.
The proof was produced by a group of agents, using an OpenAI next-generation model significantly more capable than GPT-6 Astra.
The problem concerns whether the description of smooth three-dimensional fluid motion modeled by the Navier-Stokes equations can break down. It has remained unresolved for roughly 90 years.
alex debayo-doherty retweeted
GPT-6 Astra recreated the Palace of Fine arts in Blender.
This is favorite building in San Francisco because it was built for the World's Fair in 1914 where the steam locomotive and telephone were showed off. It was a time when technology gave us all a deep sense of optimism for the future.
I feel like some of that sense has been lost since, but I hope models like astra can help restore it, and push us towards a more hopeful future.
alex debayo-doherty retweeted
Fable 5.1 is a beast at many things but one thing in particular I have been having a ton of fun with is generating videos through code.
For this one I gave it a picture of a property lot. It designed a house for the lot, rendered it, and produced a cinematic walkthrough.
alex debayo-doherty retweeted
I've been thinking a lot about the Prologue of Vernor Vinge's A Fire Upon the Deep as we're starting take off. Highly recommend the 5min read.
baen.com/Chapters/-081251528…
alex debayo-doherty retweeted
Powerful AI will change our institutions. Yet most of our attention is on aligning or regulating AI, while treating our institutions as fixed.
Introducing Pax Machina: a new publication about the institutions we need for powerful AI.
It is edited by @MaxKronerDale, @sebkrier, @NoemiDreksler, @LiamPatell, @chelcott9, @synchroaphasia, @ryan_t_lowe, @edelwax, and @klingefjord.
The editorial board consists of Peter Railton, @sethlazar, @saffronhuang, @AmmannNora, @xuanalogue, @IasonGabriel, @hamandcheese, and @deanwball.
Our goal is to seed rigorous debate about what a world of humans and powerful AI could and should look like.
We will publish proposals for new institutions, counterproposals, well-justified design principles, and analyses that change how a class of institutions should be designed.
alex debayo-doherty retweeted
Terence Tao posted his ChatGPT session trying to understand the Jacobian conjecture counterexample. It's so lovely reading a slice of how his mind works, the connections he's making, etc.
chatgpt.com/share/6a5fdc7a-d…
alex debayo-doherty retweeted
New Anthropic research: A global workspace in language models.
Of everything happening in your brain right now, only a tiny fraction is consciously accessible—thoughts you can describe, hold in mind, and reason with.
We found a strikingly similar divide inside Claude.
alex debayo-doherty retweeted
AI labs won’t sell intelligence as a product.
They will sell products of intelligence.
The two most valuable products of intelligence are
1) Scientific inventions
2) Entrepreneurship: running companies
These will be the biggest sectors of growth in frontier ai as routine software becomes cheap commodity.
If we rely on frontier labs for open api access to frontier intelligence we will be grossly disappointed.
They don’t want to sell you intelligence, only its products.
We need open networks to maximize individual agency post AGI.
Anthropic launches Claude Science in push for pharma revenue ft.trib.al/Rg9ly0o
alex debayo-doherty retweeted
i wish i could do more - i wish i had a thousand hands and a thousand eyes and a thousand years and army of angels and a thousand stars that lit the sky so bright that the night would never come and that our sleepless dreams would fill this world
alex debayo-doherty retweeted
It's Sunday June 12th, 2016 and the world is mourning the victims of the Pulse nightclub shooting. Trump, who recently clinched the Republican Party nomination, posts on Twitter that Obama should leave office over the shooting.
You walk to a nearby cafe thinking about the possible implications of Move 37 (played a few months prior) and how neat the SpaceX reusable rockets are.
On the way, a mysterious gentleman pulls a newspaper out of his cloak and hands it to you. It's dated June 12th, 2026.
Top Headlines:
- Elon Musk Becomes World's First Trillionaire as SpaceX IPO's
- Department of War Publishes Third Release of Unidentified Anomalous Phenomena Files
- Citing Safety Concerns, Trump Administration Places Anthropic's New 10T Parameter AI Models Under Export Control
Huh? Still holding the newspaper, you look up... but the mysterious gentleman has already vanished. You look down... the headlines are also gone. Sipping your coffee, you think to yourself "Wow, these art students sure are are getting stranger and strfr!"
Before heading home, you find yourself checking the price of BTC... honestly, $600 per BTC seems pretty high. Maybe it's time to sell??
alex debayo-doherty retweeted
You need to be slowmaxxing. You need to be reading long, fat books. You need to be making 48-hour chocolate chip cookies. You need to spend hours watching wildlife, you need to spend 15+ min making your coffee. You need to breathe in and breathe out. You need to be slowwwwwwwwww.




























