Lean's Summer of Soundness Bugs: How AI Found and Fixed Them
What mathematicians should know about the Lean Theorem Prover: reliability & AI
Thomas Hales explains why the Lean theorem prover is crucial for reliable mathematics and how AI is making autoformalization practical. He details the 'Summer of Soundness Bugs' in 2026, where AI tools uncovered critical kernel flaws, including one that produced a false proof of the Collatz conjecture. Hales argues these discoveries are a positive development, as they were found by security researchers and quickly fixed, ultimately strengthening Lean's reliability.
The 'summer of Lean soundness bugs' might sound like a disaster, but closer investigation shows that the detection of these soundness bugs is a positive development.
- chr15m
Will we ever see a soundness bug in the lean kernel again?
To a software developer the question seems insane. There were bugs in the past, of course there will be more.
When we see those bugs, what will it mean for AI lean proofs? Can we trust them?
This whole thing boils down to trust.
We can trust human verifications highly because of community and reputation and human proof-of-work. Humans sometimes lie about math results but it's rare because of this. They make mistakes and those mistakes are discovered by communities who are themselves largely trustworthy because of this.
LLMs don't care about reputation. They hallucinate and fabricate often. In harnesses they literally try to cheat and bend rules, which is a disaster for knowledge that is encoded in rules. So we have to rely on proof checkers.
The problem is, how trustworthy are proof checkers? Are there bugs? And is the underlying theory itself free of paradoxes and unknowables and mathematical "bugs" that can be exploited? Imagine a human mathematician hell bent on deceiving other mathematicians - would we trust their breakthroughs, even with a verifier?
Because of these properties, the final backstop has to be humans, and rooted in the community and proof-of-work based human trust system. At the moment people are trusting the tools too much.
Prediction: bugs will be found by humans using AI tools that call into question the Navier-Stokes proof.
- rramadass
The article already mentions the paper, Sets in Types, Types in Sets by Benjamin Werner which maps between Set/Type theories.
Another related and more approachable paper on the evolution of Type Theory and its relation to Set/Category theories is Types, Sets and Categories by John Bell.
Finally also see, Typed Lambda Calculus / Calculus of Constructions by Helmut Brandl for an excellent book-length but concise overview of CoC/CIC.
IMO, the above is required reading to understand theorem provers and proof assistants. In particular, Brandl's work is a must-read.
- JonChesterfield
> Autoformalization has become a practical reality in 2026
Uh, _maybe_. I've been translating papers into lean for the last week and the correlation between the formalized result and the papers is extremely poor. The cycle seems to be "have a go at the paper, it's a bit hard, prove something different, proclaim success". It's still faster than doing it all by hand but paper in -> lean out in no way ensures a correspondence between the two.