Aggelos Biboudis

Slides for my JavaOne 26 session are now available online: 🔗cr.openjdk.org/~jfumero/prese… #java #gpu #cr #performance

New on "Proofs and Intuitions": Verifying Move Borrow Checker in Lean: an Experiment in AI-Assisted PL Metatheory. proofsandintuitions.net/2026/03/18/mov… The gist: I formalised Move's type system in Lean: 39KLOC, under a month, with Claude. Person-years in PL research are now person-weeks.

One of the cool thing about the AI revolution is that spending a lot of effort on error messages is cool again, because the agents actually read the error messages!

🦾Meet Aristotle Agent, the world’s first autonomous mathematician — live and currently free of charge. We designed Aristotle Agent to solve and formalize the world’s most challenging mathematical research problems. It is now: ☑️#1 in Formal Math: We’re the #1 formal math model according to ProofBench, by @ValsAI, ahead of the closest competitor by 15%. Aristotle Agent can autonomously prove/formalize for up to 24 hrs without human intervention. ☑️Fully Agentic: Give it an English problem and it will prove/formalize from scratch, or it can work and edit files directly inside your Lean project / repository. ☑️Github-ready: Aristotle agent produces repo-quality code; project leads are increasingly merging Aristotle-drafted PRs with no modifications. Now live across both web, CLI, and API. 🔥

Java powers billions of devices and millions of enterprise apps. Bringing AI to those systems means getting reliability, security, and modernization right. At #JavaOne, Patrick Chanezon and @bbenz showed how. Watch "Java for an AI World": youtube.com/watch?v=3fLCOq…

Java 26 is now available! #Java26 #JDK26 #OpenJDK ☕ Download Now: social.ora.cl/6018B6ynbo ☕ Release notes: social.ora.cl/6019B6ynbU ☕ API Javadoc: social.ora.cl/6010B6ynbq ☕ Features: social.ora.cl/6011B6ynbS ☕ Inside Java on JDK 26: social.ora.cl/6012B6ynbs

Excellent Career Advice

Just a few years ago, combining AI and formal mathematics was science fiction. Now it's happening. Interview with @ETAPSconf on Lean, AI, and why formal methods have never mattered more. etaps.org/blog/043-leo-d…

Formalizing a proof in Lean using Claude Code. ~ Terence Tao. youtu.be/JHEO7cplfk8 #LeanProver #ITP #AI4Math

Terence Tao: Formal Verification Breaks the Trust Barrier in Mathematics Formal verification is transforming mathematical collaborations — enabling anonymous contributions, machine-checked proofs, and radically more precise scientific discussion.

@satnam6502 I haven’t seen more enthusiastic crowd than people understanding, reading, reverse engineering/disassembling and changing low level assembly code with LLMs. Maybe your observation is indeed very much related to that as well.

goto makes a comeback. The goto rule might be simple but Hoare pointed out its application is complicated for human brains, but LLM-code generators don't care.

Optimizing GPU Programs from Java using Babylon and HAT. social.ora.cl/6010C4pYp

AI is writing a growing share of the world's software. No one is formally verifying any of it. New essay: "When AI Writes the World's Software, Who Verifies It?" leodemoura.github.io/blog/2026/02/2…

We rave about giants like Newton, Einstein, Bohr, Tesla, and Edison. But in terms of direct impact on our lives in the information age, nobody comes close to Claude Shannon. In 1948, he dropped a straight 10/10 paper: A Mathematical Theory of Communication. His work has imbued us with the ability to send whispers across continents. The paper doesn’t just suggest techniques, it draws the boundaries of reality for information... how far compression can go (entropy), the maximum rate a noisy channel can carry reliably (capacity), and why error correction isn’t optional if you want those whispers to arrive intact.

Want to learn more about code reflection? Then be sure to join Paul Sandoz at #JavaOne! Use code J12026YTS when you register to save $100 off your JavaOne registration. social.ora.cl/6013hejcc

The CSLib steering committee recently announced the official launch of CSLib — an open-source effort to formalize computer science in Lean, inspired by the impact of Mathlib in mathematics. CS researchers, practitioners, and enthusiasts are invited to get involved to support formalizing essential computer science concepts, and building infrastructure for reasoning about real-world code with Lean. Learn more at: 🌐 cslib.io 📄 White paper: arxiv.org/abs/2602.04846 🤝 Contribute: github.com/leanprover/csl… #LeanLang #LeanProver #CSLib #OpenSource #FormalVerification

"Package Managers à la Carte, A Formal Model of Dependency Resolution" preprint out today: a new package calculus to describe the cambrian explosion of systems that exist today arxiv.org/pdf/2602.18602

I wrote an essay on proof assistants in the age of AI. leodemoura.github.io/blog/2026/02/1…

@rickasaurus I am starting to think that it uses unknown technical terms when it tells you "should I do X and Y for you?) so that you keep asking. Is it my impression that it deliberately puts you in a technobabble when you start digging more? This is very different from education.

ChatGPT 5.2 is the Windows 8 of ChatGPT models

The POPL program is up! conf.researchr.org/track/POPL-202…