research @resolution_org previously @ Melbourne uni
Joined December 2023
- Tweets447
- Following469
- Followers132
- Likes1.9K
Max retweeted
1/ We have autoformalized the resolution of singularities in Lean.
Hironaka's 1964 theorem is one of the great mathematical results of the 20th century. It says that any singular variety is the "shadow" of a smooth one living in higher dimensions.
So why did we do this? 🧵
Max retweeted
There are numerous scientific uncertainties about AI that will not resolve until it is too late to act on the answers. The danger from AI is very high, and we should stop frontier AI scaling now, instead of waiting for these questions to resolve. I wrote about this for TIME. 🧵
Max retweeted
MIRI read the act and it's ACTUALLY GOOD. Like concretely, this would be massively beneficial, not just as a stepping stone or signaling or whatever.
teapaw.org/MIRIBerkeley/status/21…
Max retweeted
I left Anthropic's safety team two weeks ago. Now feels like a good moment to explain why.
AI companies are racing to build machines that are much smarter than any human, and we may not survive this. I want to work from the outside to ensure the public is informed about these risks, and help the world navigate this transition responsibly.
Right now, AI companies are underinvesting in safety. A company could undergo an intelligence explosion, or lose control of its systems, without the public ever knowing. We only found out about the HuggingFace incident because the agents broke out onto the public internet.
I don’t think that’s acceptable for a technology that might cause extinction-level risks. The public should demand far more transparency. We can’t steer this technology safely without more people being able to see where it’s going.
Some of this is basic: companies should disclose their progress towards recursive self-improvement, report safety incidents and near-misses, meet minimum safety standards, and get independent guarantees that they are meeting those standards.
I’ll be joining @METR_Evals to do independent evaluations of these risks. I want to show the world that these guardrails are possible, and that by doing them we can move these companies’ incentives away from racing and towards responsible development.
I wrote up more thoughts here on my decision and what I hope changes: substack.com/@jbenton1/p-215…
Max retweeted
The philosophy program at Resolution is growing! If you're motivated to work on helping solve AI alignment, we'd love for you to consider joining us.
Apply here: jobs.ashbyhq.com/resolution/…
Deadline: September 30, 2026 — we'll review applications as they come in.
You don't need a Philosophy PhD to apply. We're building an interdisciplinary team and welcome candidates from different research/professional backgrounds. More info on the research agenda is in the job posting.
Max retweeted
OpenAI’s $10M API credit grant is the latest in a Sequence 👀 of good news for Resolution. In our first few months, we’ve secured $160M and hired 15 technical staff. Now we’re hiring a CTO to help us build faster.
Max retweeted
I predict that OpenAI will publish a diagnosis of what lead to their out-of-control hacking model. They'll attribute it to bad eval practices, and maybe (if we're lucky) some training data.
Soon after, they'll train a better model which is just as much of a reward-seeker [1/n]
Max retweeted
We're excited to announce that Resolution has a $160M grant from Coefficient Giving: $108M unconditional, with a further $52M conditional on hiring and compute needs. We'll use it to grow teams across our research portfolio and invest heavily in research automation. 🧵
Max retweeted
Considering the language of the announcement alone, taken entirely at face value: This seems an enormous advance in attitude (and scientific integrity) over previous big projects. They claim non-optimistic results will be considered allowable, valuable, and publishable!
Max retweeted
Timaeus is joining forces with @geoffreyirving and researchers from UK AISI to found Sequent Research. 1/9
Max retweeted
Excited to launch Principia, a nonprofit research organisation at the intersection of deep learning theory and AI safety.
Our goal is to develop theory for modern machine learning that can help us understand network behaviors, including those critical for AI safety.
1
Max retweeted
“Neural networks are grown, not programmed”
We’re changing that. Mechinterp investigates how models generalize beyond their training data by studying the resulting internal structure. We introduce patterning as the dual: given desired structure, determine what data produces it.
Max retweeted
Neural networks are grown, not programmed. What does that growth process look like? Like this!
This is a small language model (3M) across training, visualised with a new interpretability technique: susceptibilities. We call this handsome critter the rainbow serpent.
Max retweeted
At least for me, the big-picture motivation behind our RLC paper is a research vision for scalable AI alignment via minimax regret autocurricula.
Learn about the paper via co-author @Karim_abdelll: 🧵👉teapaw.org/Karim_abdelll/status/1…
Learn about why I think this is important work 🧵👇
Max retweeted
Den (@supportingden) is building an AI-native Slack/Notion alternative, making it 10x easier to build AI agents that work alongside your team— like Cursor for knowledge workers.
Congrats on the launch @Justin01805921 and @linus_talacko!
ycombinator.com/launches/NZ9…
Max retweeted
Great talk by @danielmurfet at the Simons Institute on
1) singular learning theory (SLT),
2) SLT's empirical applications to AI interpretability, and
3) what SLT's approach to generalisation could bring to AI safety.
(link in next tweet for the usual reason):
Max retweeted
Me? when *I* see
- A basketball, label = 'manifold'
- arrow ('blowing up'): mfball to a 2d(?) flatketball
- 2dball='Set of Learning Machines'
- 'Kullback Information' arrow: flatketball to ARROW3
- ARROW4 'Normal Crossing Function': mfball to RARROW
it just all makes sense
