Emanuele Natale (@emanatale) header
Emanuele Natale (@emanatale) profile picture

CNRS researcher at I3S (Université Côte d’Azur) and INRIA Sophia Antipolis.

Nice, France
Joined June 2016
Photo by Emanuele Natale (@emanatale)Photo by Emanuele Natale (@emanatale)Photo by Emanuele Natale (@emanatale)Photo by Emanuele Natale (@emanatale)Photo by Emanuele Natale (@emanatale)Photo by Emanuele Natale (@emanatale)Photo by Emanuele Natale (@emanatale)Photo by Emanuele Natale (@emanatale)Photo by Emanuele Natale (@emanatale)Photo by Emanuele Natale (@emanatale)
As a PhD student at Sapienza, I had the pleasure of speaking with Alessandro Panconesi on several occasions and attending study groups he organized. His advice had a profound impact on me. Deeply saddened by his passing. uniroma1.it/it/notizia/cordo…
26
Congratulations for the achievement!
Timo Keller and I have posted our resolution of questions of Venkatesh, Bost–Charles, Frey–Kani–Völklein, and going all the way back to Ihara: arxiv.org/abs/2610.06461. We construct Golod–Shafarevich towers in dimension 2, i.e. infinite (geometric) unramified towers of arithmetic surfaces. The general vibe was that such surfaces should not exist. Timo and I laid out our program to construct them back in 2022: that is more or less the first half of the proof. This summer, helped by a little army of AI agents, we managed to finish the climb: we used GPT 5.6 Sol, Fable and Aletheia internally at Google DeepMind. The experience is described in some detail in Section 1.4 on page 5: it has been by far the most exciting human-AI collaboration that I have personally taken part to, so far. Simultaneously and independently, Pablo Chenal has also settled the questions of Bost–Charles, and consequently Frey–Kani–Völklein: arxiv.org/abs/2610.05972. Pablo gives a much shorter and more elegant existence proof, while our approach is heavier but makes the surfaces explicit. Pablo, Timo and I are currently working towards a unified perspective and merging the two works into one. I have been dreaming of finding such a surface since 2022, and it is truly exciting to be able to finally share it!
1
1
227
"#French has an alphabet of 26 letters (plus 13 accented vowels, 1 consonant with a cedilla, and 2 ligatures), slightly fewer than 40 sounds (or phonemes), and... around 700 ways of writing them (or graphemes)." These, for example, are all the same sound:
1
1
57
Emanuele Natale retweeted
As correctly mentioned in your technical paper, 3 papers solved the first "open" problem on Gaussian ellipsoid fitting, in August. AI scooped by humans?
mathematicians and muse spark collaborated to solve 6 open problems in math: 1. The Strict Threshold for Gaussian Ellipsoid Fitting 2. Finite-Time Blow-Up of Radial Negative-Energy Solutions for the Mass-Critical Biharmonic Nonlinear Schrödinger Equation 3. Semiabelian Groups Need Not Be Monomial 4. Tightness of the Cycle-Based Relaxation for Completed Length-Three Alpha-Cycles 5. String Two-Point Function = Height Function on a Curve 6. On Solvable Evolution Algebras and a Conjecture by García-Martínez and Pérez-Rodríguez
2
4
1
56
6,105
Emanuele Natale retweeted
theorydish.blog/2026/09/29/s… blog post by theoretical computer science prof at Stanford, Omer Reingold: “Above all, we need to reevaluate our identity. What is it that makes mathematical knowledge and research valuable? What are we offering society, and how much of it survives in a world where models match or exceed humans in some or all relevant mathematical skills? For quite some time, the implicit social contract has been that society pays us to exercise our intellectual curiosity and we, in return, provide useful skills to the next generations and practical knowledge for the world. The current crisis is driven not only by the power of LLMs, but also by how rarely we have had to examine or articulate this contract. Now that the deal needs to be renegotiated, we should approach it with humility rather than entitlement.”
10
78
16
442
84,201
Emanuele Natale retweeted
update: our arXiv rejection made it to NeurIPS!!!! hal.science/hal-05708820v1/d… “08/26: Thank you for submitting your work to arXiv. We regret to inform you that arXiv's moderators have determined that your submission will not be accepted and made public on arXiv.org.”
22
24
10
489
92,688
And then we attacked them with AI. More than 30 now have a complete proof or an explicit counterexample. Some have already been checked by mathematicians, a few formalized in Rocq. We welcome reviewers! github.com/graph-theory-AI/G…
More than 800 conjectures in graph theory. If you still have Fable credits, give it a try! mlelarge.github.io/graph-con…
1
7
7
558
Sadly, French research institutes do not allow us to use research funding to pay for US-based AI services. I have desperately tried to explain that much of CS research does not involve sensitive data, without success... 😔
Nowadays, doing a PhD only makes sense if your advisor is happy to support at least one 20x plan (and maybe a 100x one someday). Luckily, that’s actually true in our lab. It’s basically a requirement now lol. Really, really grateful to both @zicokolter and Kaiming for pushing for this ages ago — and especially to Zico for actually footing the bill. ❤️
1
59
Emanuele Natale retweeted
Always stunning to see how much the quality of NeurIPS reviews depends on the subcommunity a paper is sent to. But the worst fate is for papers that do not clearly belong to any community: they end up torn apart in a no-man’s-land of confident misunderstanding and bitterness.
7
6
3
227
25,687
I wrote an agent skill for using Grid'5000 with LLM coding assistants. Grid'5000 uses the OAR scheduler, which these tools rarely know well. The skill is a single Markdown document capturing the correct commands and conventions. github.com/natema/grid5000-s…
1
2
46
The first Jean Zay (IDRIS) skill to use France's national supercomputer with AI coding agents, packaged so your agent knows everything it needs 👇 github.com/natema/jeanzay-sk… cc @Genci_fr
2
36
An open-source AI that reads published mathematics for mistakes. We ran it over 300+ graph-theory papers and had it adversarially double-check its own findings. Several authors have already told us the feedback was genuinely useful! 🔗 github.com/natema/mathpocaly…
1
1
47
My institute uses @Zimbra, for which none of the major LLM providers offer a connector. So I built zmail: a zero-dependency CLI + skill.md that lets any AI agent read, search & draft email in a Zimbra mailbox over IMAP. 👇 github.com/natema/zimbra-ski…
115
I wanted a dead-simple way to spin up a throwaway Linux VM to run untrusted code in. mkvm: one command → a booted Ubuntu 24.04 VM, SSH key already in it. One Bash script, no config, runs from curl. MIT. github.com/natema/mkvm
1
33
Emanuele Natale retweeted
I have my own theory here: many mathematicians have started using top-tier models and agentic systems. The effect is that they are finishing up very old projects that were left untouched for years. They realized that they had all the required ideas and tools but did not have a person to wrap things up. I think this "vacuum cleaner effect" will last for the next few years and will end up with a complete stall in most areas of mathematics. What will remain are very hard questions, and possibly some new ones. But once a question is within reach of the agent, it will get published almost automatically. People will remember this period of civilization as the "great purge of ideas". The outcome will be a vast intellectual startup where everyone is at ground zero, and the occasional genius will pop up to scale their ideas and drain it again until the thread dies.
I wonder what happened in the last few months to make this happen... Last quarter of math articles on ArXiv is around 20% higher than expected based on previous years
44
121
11
783
88,574
Emanuele Natale retweeted
We believe every mathematical breakthrough should be automatically verified in Lean. That means formalizing all of mathematics—and this will require us to run agents at an extremely large scale, perhaps burning through billions of tokens. We hope that Leanstral can be the foundation to get there.
2
2
74
11,140
Congrats to @nowathom for his github.com/BioDisCo/paper-ba…. I was thinking about something similar, a "Lean coverage" badge analogous to the concept of code coverage in software engineering.
1
28
If you're into theory, check out also the EATCS Bulleting Viewpoint Column eatcs.org/images/bulletin/be… by @MatthiasFue and him.
1
21
I always had an engineer’s soul. As a kid I’d tear open electrical toys to rebuild them. I became a scientist, but hated theorists joking about engineers. Engineering built the AIs now outperforming most of us at short-horizon theory. Victory for the builders.⚙️
24