AI Researcher @ Mistral AI | Formally IBM Research | Former Mathematician/Logician/Data scientist | Building AI for math and reasoning
Joined July 2022
- Tweets 499
- Following 229
- Followers 707
- Likes 1,810
1 Photos and videos
Pinned Tweet
Mar 16
Announcing our fully open source code agent to support development in @leanprover. This has been a labor of love by our team at @MistralAI and we look forward to seeing what the #LeanProver community does with it!
1
28
161
10,474
Jason Rute retweeted
Mar 28
Leanstral by @MistralAI is now available in OpenProver!
openprover theorem.md --model=leanstral
Mar 23
I'm releasing OpenProver v1.0.0!
It's 1) an open-source automated theorem prover inspired by DeepMind's Aletheia (@tonylfeng @gjb_ai @lmthang), and 2) a "Claude Code for mathematicians", allowing interactive proof search in English and formalization in Lean.
1
17
71
6,431
Jason Rute retweeted
Mar 25
Interested in Lean and near 🇫🇷 Paris?
The inaugural Paris Lean Meetup is happening April 24 at 7:00 PM, hosted by Mistral AI.
Two talks: Leonardo de Moura of Lean FRO, and the Mistral team introducing Leanstral, their open-source code agent for Lean 4.
Pizza and informal discussion afterward.
🔗 Registration details here: meetup.com/lean-paris/events…
4
16
158
12,840
Mar 23
Someone built an app for Econ Autoformalization in Lean using #Leanstral. Looking forward to seeing more tools like these!
Mar 23
I would love some expert guidance on how to get the most out of leanstral. Here is the API’s repo and a little demo im working on with lovable. Happy to chat outside the thread!
leanecon-demo.lovable.app/
github.com/Bonorinoa/lean_ec…
1
3
14
1,382
Jason Rute retweeted
So far, it has been absolutely great to work with. Thank you to the entire #Leanstral team this is exactly the kind of project we need more people working on.
1
1
177
Mar 17
Thanks, @Leonard41111588 ! And thanks for making such an awesome language! We really hope #Leanstral is a benefit to the Lean community, and we are actively working on making it even better!
Congratulations to the Mistral team! Great to see a dedicated open-source Lean 4 coding agent. The Lean community is growing fast, and tools like Leanstral will help more people get productive with Lean quickly. Looking forward to seeing how it evolves.
1
2
20
1,363
Mar 16
Announcing our fully open source code agent to support development in @leanprover. This has been a labor of love by our team at @MistralAI and we look forward to seeing what the #LeanProver community does with it!
1
28
161
10,474
Mar 16
Use for free in Mistral-Vibe:
$ uv tool install mistral-vibe --upgrade
$ vibe /leanstall
Then shift tab to lean mode
1
17
601
21 Dec 2025
Last time I saw someone drop a Lean “proof” of a Millennium Problem it didn’t remotely compile. I hope in this case the error is at least interesting. :)
20 Dec 2025
Update: David claims to have a Lean proof of Navier-stokes, which he is publishing tonight.
I have accepted a $10,000 bet that he's mistaken.
8
2
143
19,465
Jason Rute retweeted
1 Oct 2025
Thrilled to announce @MistralAI's new formal math team following our $2B funding round.
AI for formal math researchers wanted. We offer:
- Work on creating the state-of-the-art prover, autoformalizer, and automatic proof agent all in one model
- World class team (with @JasonRute @sorgfresser @Icannos myself and support from @GuillaumeLample)
- A huge bias for action
- Hundreds of GPUs per capita with Mistral’s bleeding edge reinforcement learning pipeline (responsible for Magistral and Magistral 1.2)
- Open research with publications
- Industry-leading salary
- Offices in Paris, London, and Palo Alto
To apply: Experiences in AI required. Send your CV and best work on AI and/or formal math to aj@mistral.ai, with <formal> in the email title.
16
48
519
79,984
16 Jul 2025
For those using @leanprover AI models to “compete” in #imo2025 (@ProjectNumina , @KaiyuYang4), what Lean formalizations will you use? (A) autoformalized statements, (B) manually formalized statements, (C) Joseph Meyer’s IMOLean formalizations (github.com/jsm28/IMOLean)?
2
3
20
2,056
16 Jul 2025
(A) Is the least hand holding, but it could misformalize. (B) Makes sure the formalization fits your model’s constraints, but leaves you open to criticism. (C) Joseph has thought more about IMO Lean formalization than anyone I know, but his may not fit your model’s requirements.
1
483
14 Jan 2025
That the area of the Mandelbrot set is computable.
13 Jan 2025
1
1
3
1,072
14 Jan 2025
At #JMM2025 last week, a mathematician told me he used ChatGPT (forgot which version) to get a major insight into solving his math problem. But, he is reluctant to share publicly (e.g. in his paper) that this happened since it could make him look less bright. I find this sad. 🧵
3
4
68
8,724
14 Jan 2025
If we aren’t willing to talk about when tools are helpful, it will lead to an asymmetry where those in the know will use hidden methods that they keep secret out of either embarrassment or competition. IMHO, this isn’t in the spirit of mathematics research.
2
25
1,349
14 Jan 2025
I have no idea if LLMs are any good as math collaborators for bouncing around ideas and brainstorming, but if those who do get this to work keep it a secret, we just won’t know. We should be rewarding those who use them wisely for their research.
1
1
19
1,128
10 Jan 2025
Remind this is in an hour: 8am in Skagit 3 (Lower Level, Seattle Convention Center Arch 800 Pike)
9 Jan 2025
I’m really excited to announce that I’m going to be at the Joint Math Meetings #JMM2025 @JointMath to give a talk on AI for Formal Theorem Proving on Friday. Reach out if you want to talk about AI for Math, or for all my math friends, if you just want to catch up!
1
4
708
Jason Rute retweeted
9 Jan 2025
I’m really excited to announce that I’m going to be at the Joint Math Meetings #JMM2025 @JointMath to give a talk on AI for Formal Theorem Proving on Friday. Reach out if you want to talk about AI for Math, or for all my math friends, if you just want to catch up!
1
4
16
2,411