Kirsten Henningsgard retweeted
Fifty years of C and we're still shipping buffer overflows.
Aristotle proves your C does what you said it should. When it doesn't, you get the input that breaks it.
New sign-ups get $500 in credits. Get started with the most effective way to protect your enterprise:
aristotle.harmonic.fun/?r=x
Kirsten Henningsgard retweeted
C and Verilog are just the start. More languages are on the way.
Try Aristotle today: aristotle.harmonic.fun/
Kirsten Henningsgard retweeted
Aristotle can now formally verify Verilog and C!
On @TensordyneInc's most complex block, with 12.2M gate equivalents, 1.24M flops and hundreds of state machines running concurrently, it proved 185 whole-block properties and found bugs up to 110,000 cycles deep.
Kirsten Henningsgard retweeted
LET'S GO!!!!
I've learned more in the last two months than in the last six years. So grateful I got to help turn Aristotle's math expertise toward code and chips.
🚀🚀🚀🚀🚀
Kirsten Henningsgard retweeted
atp there's no reason to accept memory safety issues in C code
oh my. pointed aristitle at TorchLean's C runtime code and in ~6 hours: 211 of 213 properties proved (memory safety, refcounts, functional correctness)
The other two came with a use-after-free counterexample involving inconsistent caller reference counts. We are reviewing the ownership assumptions and proof artifacts to establish exactly what’s guaranteed: ) im very impressed!
Kirsten Henningsgard retweeted
We've been working on verifying software and hardware, so that we can eliminate bugs in the most important parts of the technology stack, and let models autonomously iterate without compromising on correctness. I'm super excited we can now make this technology available to all!
Kirsten Henningsgard retweeted
Today we’re bringing Aristotle to software and hardware!
Describe the properties your code must satisfy and Aristotle formally verifies that it meets them.
I’ve spent the past few months helping Aristotle expand from proving math to verifying code. I’m excited to see it available to everyone today.
Try it: aristotle.harmonic.fun
Kirsten Henningsgard retweeted
Formally verify SystemVerilog and SVA (or autoforamlized properties).
Prove memory safety about your C programs.
Prove a C model is equivalent to its SystemVerilog implementation.
Our AI theorem prover is now publicly available.
Try it out at harmonic.fun
Kirsten Henningsgard retweeted
oh my. pointed aristitle at TorchLean's C runtime code and in ~6 hours: 211 of 213 properties proved (memory safety, refcounts, functional correctness)
The other two came with a use-after-free counterexample involving inconsistent caller reference counts. We are reviewing the ownership assumptions and proof artifacts to establish exactly what’s guaranteed: ) im very impressed!
Kirsten Henningsgard retweeted
This is an interesting development!
@HarmonicMath started with doing math, but now is moving away towards coding.
Financially this seems reasonable: verifying code is a much bigger market!
It could be a sign that big-AI will move away from research math.
I have been using harmonic math Aristotle for the past year, roughly, or even I think since it came out whenever that was. This is actually a huge improvement and I’m extremely excited. I hope that the next thing they add is something like Rust.
Kirsten Henningsgard retweeted
We’re bringing Aristotle to code.
AI is writing more code than anyone can review. We're building the AI that verifies it.
Starting today with C and Verilog.
Kirsten Henningsgard retweeted
We taught an AI to prove math. Next, something harder to get right. Soon.
Kirsten Henningsgard retweeted
A pleasure to help @wtgowers and his colleagues get their preprint formalised with Aristotle (@HarmonicMath).
The long case analysis that a referee would understandably prefer not to check by hand is now formally verified in @LeanProver.
The code should be available on @GitHub before long. After some further cleanup, parts of the supporting API may also be suitable for upstreaming to Mathlib.
Kirsten Henningsgard retweeted
BREAKING: Aristotle now powering formal verification of Solana smart contracts
"Prove your Solana code is correct. Mathematically"
Replying to @shek_dev
two major upgrades that made this possible
asm2lean: assembly to Lean transpiler, no manual transcription hell
aristotle by @HarmonicMath : the agentic prover can run for upto 24 hours on harder theorems nitter.cf/HarmonicMath/status/20…
Kirsten Henningsgard retweeted
Tudor Achim (@tachim) is the co-founder and CEO of @HarmonicMath, a startup working to solve one of AI’s hardest problems: mathematical reasoning.
In our conversation, we explore:
• Why Tudor believes math is the fundamental toolkit to understand the world
• How Aristotle works and the applications beyond pure mathematics
• The reinforcement learning process that lets Harmonic generate synthetic training data and solve problems humans have never attempted
• Why Tudor believes AI could surpass human mathematicians on specific tasks within 2–3 years
• Why the future of mathematics looks more like GitHub than academic journals
Thank you to the partners who make this possible
- @brexHQ: The intelligent finance platform: brex.com/mario
- @Guru_HQ: The AI source of truth for work: getguru.com/
- @Rippling: Stop wasting time on admin tasks, build your startup faster: rippling.com/mario
Timestamps
(00:00) Intro
(06:28) The mathematical foundations of music (and why Tudor keeps them separate)
(12:52) Defining intelligence
(22:55) The two breakthroughs that made mathematical AI possible in 2023
(35:25) An overview of Aristotle: the world’s first always-correct mathematical agent
(45:34) Math in AI now and what’s next
(56:02) History’s alternating rhythm of thinking and measuring
(1:00:18) Final meditations
Kirsten Henningsgard retweeted
Update: Aristotle has been used to autoformalize 105 of the 115 Erdős problem formalizations produced by AI tools, i.e. 91% of the total.
This includes formalizations of classical proofs such as Pólya (1918), Barrow and Mordell (1937), Hall (1947), de Bruijn (1951), and Lorentz (1954), alongside very recent proofs such as Tao (2026), He–Li–Tang (2026), Pomerance (2026), and Chojecki (2026).




















