Computer Scientist and Philosopher at Oxford. So much to do, so little time.
Joined March 2024
- Tweets667
- Following836
- Followers714
- Likes7.6K
Pinned Tweet
new post: a bit of a history of my life through the lens of ambition, anxiety and possibility
Samuel Ratnam retweeted
Hardest thing ever written award
Inspired by @Sauers_ and @jfonsecarivera and other fun recent work with personas in AI models, I built a partial neuron atlas for Talkie-1930, the historical language model created by @status_effects and @AlecRad. Here's the link: talkieneurons.vercel.app
new kind of alchemy just dropped
i made a library of 34,220 persona neurons in qwen
please help me find the weirdest ones:
qwen-neurons-site.vercel.app…
Samuel Ratnam retweeted
i made a library of 34,220 persona neurons in qwen
please help me find the weirdest ones:
qwen-neurons-site.vercel.app…
Samuel Ratnam retweeted
We excited to announce two fellowship streams this winter with @pivotal_org. Come help us with AI Alignment research during some of the most important months in human history.
Applications for this round close this Sunday. Link to apply below!
Samuel Ratnam retweeted
Announcing the Call for Papers for Oxford Studies in Philosophy of AI and Computing!
Rapid AI progress is raising *so many* philosophical questions; but philosophers aren't as involved in the conversation as they should be, for many different reasons.
One is that, aside from some work in logic and philosophy of mind, philosophy of AI and computing has often sat on the margins of the discipline. One reason for *that* is that so many philosophers working on AI have had to do so basically on their own, figuring things out for themselves as they go along, without a real community around them.
OSPAIC is going to help fix this! We're going to have an annual conference and volume. The conference (in DC! where much of the future of AI will be decided) is especially important as we think about the nature of intellectual life in a world where AI systems can one-shot a superficially-plausible philosophy paper. OSPAIC sees philosophical progress as being about more than just the accumulation of true claims. The conference is a big part of our vision for how we contribute to philosophical progress.
And our aim is also to help philosophers be part of the broader public conversation! To that end we're also going to be launching, soon, a subcode on arXiv for philosophical foundations of AI (cs.pfai), and encouraging everyone who submits to OSPAIC to also upload their draft to arXiv (at present, use keyword PFAI).
We're also partnering with @cosmos_inst, who will be sponsoring an annual prize for the best paper on philosophy and AI, as well as helping fund the first round of the conference and Open Access publication for the volume. And with Cosmos we'll be highlighting some of the most interesting submissions to cs.pfai as they come in.
I'm the executive editor; Jeff Howard (UCL) and Rachael Sterken (University of Hong Kong) are associate editors; Ned Howells-Whitaker (JHU and Pittsburgh) is the assistant editor. We're grateful for the support of a wonderful advisory editorial board, including brilliant philosophers and computer scientists from academia, industry, and civil society.
The deadline for submissions is 11.59pm Feb 14, 2027, anywhere on earth. All details are at ospaic.org.
i think free market people underappreciate the extent to which the mechanisms that make markets useful underwrite so many functions in society without any need for the exchange of money
Samuel Ratnam retweeted
Geoffrey Hinton once noticed that the tellers at his bank kept changing. When he asked one of them why, the teller didn't know, only that they got moved around a lot.
Hinton guessed the reason... if staff never work with the same people for long, it's much harder for a few of them to team up and cheat the bank.
That thought became one of the most useful tricks in deep learning. While a neural network trains, you randomly switch off about half its neurons at every step. No neuron can lean on a particular partner, so each one has to learn something useful on its own. The trick is called dropout, and it helped AlexNet win the 2012 ImageNet contest, which set off the modern AI boom. It's still built into many of today's networks.
Samuel Ratnam retweeted
BREAKING: anthropic announces verified solutions to 482 open problems in philosophy in advance of IPO
Samuel Ratnam retweeted
@cherylwoooo and I looked into cyber attack acceleration. We are moderately certain that crypto hacks accelerated in early 2026, coinciding with increasing AI cyber offense abilities. ⤴️
Links below!
[1/8] This week's cybersecurity news has been alarming. Have cyberattacks accelerated in 2026?
@jasminexli and I examined crypto hacks and ransomware data.
We find that recorded monthly crypto hacks have accelerated, though better detection may partly explain the trend.
Samuel Ratnam retweeted
Today’s discussion on the speed and scale of AI development and its potential consequences was timely and urgent.
Recent developments underline why frontier models must be regulated.
Thanks to everyone who came along, despite the terrible weather! ☔️ 🙏
@PauseAI_UK
ALT Anneliese stood with a group of other speakers in a lecture theatre.
ALT A flyer for the event on AI regulation with an indication of the different speakers, including Anneliese.
Samuel Ratnam retweeted
I think a lot of people who have become worried about AI risk in the last few months are still really sleeping on BlueDot as a place to get up to speed fast. Got this nice message a few days ago
Samuel Ratnam retweeted
The Alignment Journal publishes research on the scientific foundations of understanding, predicting, and steering artificial intelligent systems. As of today, submissions are open to everyone.
What we do differently:
- We pay reviewers, with bonuses for speed and insight.
- Review discussion is confidential, but every accepted paper is published with a “review summary” to distill the insights generated.
- Each paper is judged against our acceptance bar, not against other submissions.
- Papers under review are listed publicly, and researchers can nominate themselves to review, so each paper can reach the reviewers who know the topic best.
We seek work that builds theoretical or otherwise principled analyses of agency, robustness, incentives, interpretability, generalization, and long-term behavior, and whose significance survives the deletion of any particular model, dataset or benchmark. Empirical investigations of such ideas are welcome, and negative results are encouraged.
We are especially interested in approaches that could apply to future superintelligent systems that interact and self-improve.
You can submit your preprint in any format. Submissions are rolling and open now on the website.
If you are instead interested in reviewing or serving as an action editor (basically: an area chair), create an account on our website.
Links to submit, our scope and the reasoning behind the Journal are in the reply ⬇️
Samuel Ratnam retweeted
I would personally learn ~nothing about the monitorability of a model by knowing its architecture, if I already know about its no-CoT capabilities, which is publicly available.
no-CoT capabilities basically tells us how much computation the model can do without thinking “out loud.” Like the thing you would want to try to guess based on the architecture is how much opaque reasoning the model can do. But we can just measure the opaque reasoning abilities directly!
Samuel Ratnam retweeted
Every night my agents update a file summarizing recent surprising AI news, and that file is included in every session. This reduces distractions and increases their ambition/model-of-self-capabilities.
