
Built, audited, and led several blockchain protocols to production. Looking for what's next via @untronfi @daimo_com @getclave
Joined July 2020
- Tweets269
- Following1.3K
- Followers1.3K
- Likes65.5K
Pinned Tweet
Looking for a job.
DeFi protocols built by me are processing thousands of dollars every day. Audit firms have struggled hard and tend to find nothing in my code. Things I build just work.
You know a few blogs that referenced my research, too.
Portfolio below. DMs open.
The main, inherent problem with today's AI agents is that all suggestions they make, and all actions they take, fundamentally assume that agents like itself are not radically changing the world today and it's still just humans that drive the entire economy
2
4
112
AI is making cyberattacks far more dangerous, so at @axiom_xyz we formally verified @openvm_org to stay ahead of AI attackers.
Today we’re launching @Intrinsic_HQ to bring the same AI-powered provable security to the rest of software.
At Intrinsic, we apply AI to scale formal verification for software.
As a first result, we end-to-end formally verified @openvm_org, a production zero-knowledge proof system using @leanprover. Our verification shows OpenVM's cryptography is sound and matches its implementation.
Alex Hook retweeted
The bull case for formal verification is "Here is a reusable library of properties/specs you can import in your code" not "Here is a few million LOC of Lean for you to go over, but the model passes!"
Alex Hook retweeted
if you're a cryptographer and your repo doesn't look like this, you're probably cooked.
Alex Hook retweeted
Thrilled to announce that our @GoogleDeepMind team has cracked a major challenge in software engineering and cybersecurity: formally verifying a real-world implementation of the #Signal cryptographic protocol at the machine-code level. This proof was done using AlphaProof Code, our new AI framework for formal specification and verification.
* Paper: deepmind.google/documents/36…
* Lean code: github.com/google-deepmind/c…
* DeepMind blog post: deepmind.google/blog/introdu…
A huge shoutout to my amazing teammates: @tchajed,
@FerrousAndrew, Jonathan Katz, @pushmeet, @antonkovsharov, Karn Seth, Sam Schlesinger, @RandomlyWalking.
I started working on formal software verification 20+ years ago as a grad student. I was persuaded by Dijkstra and other computer science pioneers’ vision of programming backed up by mathematical theorems. At that time, we had to choose between automated code analysis algorithms that scaled but could only prove shallow properties, and deep manual verification that took decades of expert human work.
Thanks to progress in AI for mathematical reasoning, we don’t have to make that choice any more. Over four weeks in October 2026, AlphaProof Code agents generated more than 6 million lines of machine-checked Lean proof. We proved deep computational and symbolic security properties of the entire protocol core of Signal, all the way down to the ARM machine-code level.
This is just the first step, of course, because our goal is nothing short of verifying the world’s software infrastructure. Most cyberattacks, including the AI-powered ones recently in the news, happen because of preventable code bugs. I expect that agents for formal code analysis will eliminate these bugs one category at a time.
As our paper explains in more detail, this doesn’t at all mean humans are out of the picture! Proofs are now largely automated, but human experts will need to decide what is proved with AI assistance. AlphaProof Code offers an early glimpse of what such human-AI collaboration could look like, but many other proposals of this nature will emerge.
We have released all our Lean specs and proofs and plan to work with the open-source community on improving them. If you are building critical software and would like to apply these ideas, come talk to us!
OpenAI bars some formal verification work behind KYC-ed Daybreak Blue
closed proprietary LLMs are literally Hitler
1
3
168
The next programming language for AI agents is English
github.com/medovina/natural_… wow! natural language lean, see its worthwhile to check out recent lean projects.
1
139
— People are creating and switching to AI-friendly forks of our product en masse, as it takes us over a year to get one more chip supported, and half the hardware is still not working properly
— So we're going to finally adopt AI and fill the support matrix, right? Right?...
—:
Asahi Linux is moving everything from the MIT licence to GPLv2-or-later.
Asahi is the volunteer project that reverse-engineers Apple Silicon Macs so they can run Linux. In today's Linux 7.3 progress report, developer James Calligeros explains why: people have been using the permissive licence to take the team's work. "In some extreme cases, in-development feature code was being lifted straight out of our personal forks and published without attribution or lazily rewritten with LLM assistance to obfuscate its origin."
The report points to WINE, which switched from MIT to LGPL in 2002 for the same reason: "Those who do not learn from history are doomed to repeat it."
The same report brings real wins too. M3 Macs now install without the EXPERT flag, Thunderbolt support (USB3 and networking for now) is shipping to users, and the team got GTA IV and Fallout: New Vegas running outside the muvm VM using Google's per-process page size patches.
113
x86 formal verification is coming!
The (first?) published machine-checked proof of a security property for the end-to-end execution of a Linux process running an x86 binary statically linked against glibc.
And we believe it scales!
A joint research project with @zellic_io 🧵👇
Superlogical Rex is exceptional. AI-assisted software built by people with actual taste is the future
Can't wait to try out the iPadOS version when it's live. It has all chances to replace my MacBook for SWE work
4
11
252
Dune's trial email: "continues on Free after. nothing is charged."
Dune on day 15: tries to charge me $4k (four thousand dollars), twice
thank god for an empty card
1
9
395
Alex Hook retweeted
Small announcement: ✅ formal-git
As an experiment, over the last 2 months we've modelled ~30% of Git in Lean 4, making heavy use of coding agents, and proved >8000 theorems of varying usefulness about the implementation.
In the process of doing this we've uncovered >100 potential defects in Git v2.55, at least two of which may constitute security vulnerabilities. We've also built a DRT (differential random testing) harness and the biggest corpus of relevant pinned differential test cases for Git implementations with >10k unique tests at the moment.
We've used the test cases to test our own small internal implementation of Git in TypeScript. The next step will be to differentially test all notable public Git implementations against this corpus of tests to help improve their correctness and security 🫡 We'll be reaching out to library maintainers in due course.
If you have a Git implementation you'd like us to help you test, please reach out and let me know. We'll open-source all this eventually, after potential security issues that were uncovered are responsibly disclosed and fixed.
Alex Hook retweeted
M4 Pro progress:
🔊 all 6 speakers with Apple's tuning + headphone jack + mics
🔌 USB3 5 Gbps on all 3 USB-C ports
📷 webcam
🎞️ AV1 hardware decode, 4K60 in Firefox
💤 lid suspend
🐧 Linux 7.3
All PRs up at github.com/aurora-silicon/li…, should be in Omarchy soon
Got Linux GPU acceleration working on an Apple M4 Pro
Shoutout to @AuroraSilicon and @tiredkebab for some of their work.
If we assume Grok Bot is a form of Cursor (which is fair in a lot of ways!), then they actually managed to win back a lot of their old users who switched to Codex / Claude Code last year!
Using Cursor from its early days to late last year I was frankly sure they'd just die out
1
2
165
I shared a phishing email I've received earlier with Grok @bot, and it autonomously nuked absolutely everything about the scheme with abuse reports. The domain is now dead too
Not the best time to live in for scammers
5
138






























