Jan Hůla

[Jan Hůla @Jan_Hula]

@nasqret mathematicians with a mower is maybe a better analogy that mathematicians with a vacuum cleaner :)

[Jan Hůla @Jan_Hula]

@nasqret Indeed, attacking one piece and the rest falls without no other effort :D

[Jan Hůla @Jan_Hula]

Grateful to have been part of this project and to see @nasqret herding a bunch of stochastic parrots excited to write Lean proofs.

[Bartosz Naskręcki @nasqret]

Major announcement in mathematical formalization!

Finally, after 3 months of very intensive, nonstop work by several AI agents (Codex and Claude Code), we have settled a classification of ALL 15,973 semigroups of order 6. Every one of the 15,969 that has a finite basis now has it written down explicitly, and the remaining 4 are proved to have none at all.

The whole list of bases is produced for the first time in history. Until now, for most of these semigroups, mathematicians only knew that a basis exists; nobody had ever written one down. The formalization in Lean, orchestrated with a multi-agent approach, reached more than 5 MILLION lines of verified Lean code, one of the largest auto-formalization projects to date.

It's been an amazing joint work with @JanotaMikolas and @Jan_Hula, accompanied by senior experts in semigroup theory, João Araújo and Edmond W. H. Lee.

Our paper describing this project, "Proving at Scale for Universal Algebra", has been accepted at the MATH-AI workshop, NeurIPS 2026!

When we launched this project, we were a bit pessimistic: producing proofs for 15,973 semigroups seemed out of scope for the current technology. But with a careful setup (agents communicating through a mailbox we arranged, orchestrating the effort with a custom method of bootstrapping and auto-research), it has finally come to the finish line. The last 390 semigroups took 23 more days. The very last one needed a whole structural analysis before its proof could even be written.

[Bartosz Naskręcki @nasqret]

Major announcement in mathematical formalization!

Finally, after 3 months of very intensive, nonstop work by several AI agents (Codex and Claude Code), we have settled a classification of ALL 15,973 semigroups of order 6. Every one of the 15,969 that has a finite basis now has it written down explicitly, and the remaining 4 are proved to have none at all.

The whole list of bases is produced for the first time in history. Until now, for most of these semigroups, mathematicians only knew that a basis exists; nobody had ever written one down. The formalization in Lean, orchestrated with a multi-agent approach, reached more than 5 MILLION lines of verified Lean code, one of the largest auto-formalization projects to date.

It's been an amazing joint work with @JanotaMikolas and @Jan_Hula, accompanied by senior experts in semigroup theory, João Araújo and Edmond W. H. Lee.

Our paper describing this project, "Proving at Scale for Universal Algebra", has been accepted at the MATH-AI workshop, NeurIPS 2026!

When we launched this project, we were a bit pessimistic: producing proofs for 15,973 semigroups seemed out of scope for the current technology. But with a careful setup (agents communicating through a mailbox we arranged, orchestrating the effort with a custom method of bootstrapping and auto-research), it has finally come to the finish line. The last 390 semigroups took 23 more days. The very last one needed a whole structural analysis before its proof could even be written.

[James Whittington @jcrwhittington]

We’re excited to announce DiG-bench, a new benchmark for discovery!

Over the last few weeks we’ve been testing frontier AI models on our novel discovery games and seeing how they score. Each game is a text-based environment, so they probe discovery capabilities in the natural domain of language models, rather than requiring additional, potentially confounding, visual understanding.

TL;DR frontier models have improved a lot over the last few months. But they are still stumped by some surprisingly simple problems, even in their native text domain.

With

@cocosci_lab (@Princeton) @MITCoCoSci (@MIT) @SchmidhuberAI (@KAUST_News) @misovalko (@Inria) @tri_dao (@PrincetonCS) @RMBattleday @zebkDotCom @FraserGreenlee @akaijsa @ClareMaguire @TimMuller1 @kubicek_ales @physicscat0x7d @SukritSumant @thoughtchannel_

(1/5)

[Mikolas Janota 🇵🇹🇨🇿 @JanotaMikolas]

Can LLMs write software that reasons? https://t.co/lGaRv2wgDH #llm #smt #logic #claude

[Mikolas Janota 🇵🇹🇨🇿 @JanotaMikolas]

Our groups is opening a PostDoc position. We are seeking candidates in theorem proving, SMT, and formal verification.
https://t.co/HMH3SaQeFC

[CIIRC ČVUT @CIIRCCTU]

❗Reminder – July 10 at CIIRC: Prague Synapse, the first Prague-based workshop on neural networks and reasoning.

🎫 Free entry, limited to 50 seats.
Register at 👉 https://t.co/u5esa4erpn

@Ostravska_uni
@IDEAS_NCBR
@muni_cz
@epfl_en
@UniofOxford
@GoogleDeepMind
@ethzurich

[Mikolas Janota 🇵🇹🇨🇿 @JanotaMikolas]

We are looking for a Postdoc to join our team in Prague, with a focus on theorem proving, SMT (Satisfiability Modulo Theories), or formal methods.

[Mikolas Janota 🇵🇹🇨🇿 @JanotaMikolas]

First call for papers for the workshop Pragmatics of SAT (PoS). Since this year SAT is colocated with CP, the workshop also reflects that. https://t.co/oHlfxGAwm6

[Mikolas Janota 🇵🇹🇨🇿 @JanotaMikolas]

We are announcing the first call for papers of SC-Square 2025, the 10th International Workshop on Satisfiability Checking and Symbolic Computation, which will take place on August 2, 2025, Stuttgart Germany as a satellite event of CADE. For more, see https://t.co/PoGPUkhfjh

[Jan Hůla @Jan_Hula]

@JanotaMikolas iterated binomial coefficient could be related..it could have different k for each repetition

[Ruairidh Battleday @RMBattleday]

AE Global Summit on Open Problems for AI (London, Oct 23-24): Final Line-up and Reduced Ticket Prices: https://t.co/3RmV3G75lc

It’s a pleasure to announce the final program for our upcoming Summit on Open Problems for AI in London. We have what might actually be the best 2-day line-up of UK experts in AI research and application I’ve ever seen!

On Algorithms Day (Oct 23rd), we have leading keynotes from @GoogleDeepMind, @ucl, @MSFTResearch, @imperialcollege & @VERSESAI.
- In the morning we have a panel on new types of institutions for AI research, featuring leaders from @KingsCollegeLon, @turinginst, @ARIA_research, Cambridge Consultants & @InstituteGC.
- In the afternoon we have a panel on Current Challenges for AI/ML Algorithms, with researchers from @UniofOxford, @GoogleDeepMind, @Cambridge_Uni, @AIatMeta & @xtxmarkets.

On Applications Day (Oct 24th), we’ll begin with keynotes from @OpenAI and @responsibleaiuk, and then hear from @Spotify, Academy, JAAQ., Akord AI, Boon io, @imperialcollege & @Basecamp_Res.
- Breakout rooms by @FLFDevNetwork, No 10 Downing Street Data Science Team, @InstituteGC, Zeki Data, @join_ef & @OctopusVentures.
- Panel on AI & Education, featuring @RaspberryPi_org, Inversity, @memrise, @microbit_edu & @University of Cambridge
Panel on AI & Medicine, featuring @KingsCollegeLon, @QMUL, @DecorteFuture & @redalpine.

Come and join the debate!

https://t.co/CKWXcGkNvw

[Jan Hůla @Jan_Hula]

@cogscikid So I would say that the incentive to understand something is to being able to quickly figure out to how to reach desirable states. Also, there are clearly many levels of understanding.

[Jan Hůla @Jan_Hula]

@cogscikid Hey! I think most people would say that to understand some phenomenon means to build a causal model of it. I would just add that it can't just be any model but a model which allows to answer relevant queries quickly.

[Jan Hůla @Jan_Hula]

@cogscikid I.e. if I know some low level rules of some system (how transistors work in computer) it does not mean I understand all the high-level behavior it can produce. I need to discover the relevant high-level concepts to effectively navigate relevant state space for the current goal.

[Mikolas Janota 🇵🇹🇨🇿 @JanotaMikolas]

Sharpen your pencils! FMCAD 2024 is taking place in Prague https://t.co/ZBjAi3iUqE

[Mikolas Janota 🇵🇹🇨🇿 @JanotaMikolas]

We are opening a position for a Postdoc and PhD candidates interested in SMT, automated reasoning, and Formal Methods. More here: https://t.co/P4l7IjVihp

[Jan Hůla @Jan_Hula]

Tento týden probíhá festival Brain Awareness Week, tak jsem za Ostravskou taky něco natočil: https://t.co/oMung8fnfc
For my English-speaking friends: I'm posting a video which I shot at my uni as part of Brain Awareness Week festival. Unfortunately, it's only in Czech.

[Jan Hůla @Jan_Hula]

@SuryaGanguli @Hidenori8Tanaka The benefit of tablets like Ipad is that you can have all kinds of apps there and also browse the web. But if your main focus is on writing notes and maybe reading pdfs, I can't recommend it enough.

[Jan Hůla @Jan_Hula]

@SuryaGanguli @Hidenori8Tanaka For me, reMarkable was a game-changer. I used to have tons of papers with notes on my desk and now I write everything on the tablet. Maybe it's just me but the fact that the screen is not glowing makes a big psychological difference.