It’s great to see this pattern of people realising that agents can specify the desired behavior then write code to conform to the specs.
TDD, verification, whatever your tool; verification suites of all sorts accrue over time into a very detailed repository of documentation of how things are supposed to work that, being executable, puts zero tokens in the context when the code is correct.
It’s more powerful than reams upon reams of markdown specs. That’s because it encodes details, not intent. Your intent is helpful at the leading edge of the process, but the codified result needs shoring up to prevent regression. That’s the area software engineering has always ignored because we have gotten by on letting teams hold context in their heads and docs.
As software gets more complex we need better solutions than “go ask Jim about that, bloke’s been in the code for years”.
> Instead of taking a stab in the dark, Leanstral rolled up its sleeves. It successfully built test code to recreate the failing environment and diagnosed the underlying issue with definitional equality. The model correctly identified that because def creates a rigid definition requiring explicit unfolding, it was actively blocking the rw tactic from seeing the underlying structure it needed to match.
There have been a lot of conversations recently about how model alignment is relative and diversity of alignment is important - see the recent podcast episode between Jack Clark (co-founder of Anthropic) and Ezra Klein.
Many comments here point out that Mistral's models are not keeping up with other frontier models - this has been my personal experience as well. However, we need more diversity of model alignment techniques and companies training them - so any company taking this seriously is valuable.
Trustworthy vibe coding. Much better than the other kind!
Not sure I really understand the comparisons though. They emphasize the cost savings relative to Haiku, but Haiku kinda sucks at this task, and Leanstral is worse? If you're optimizing for correctness, why would "yeah it sucks but it's 10 times cheaper" be relevant? Or am I misunderstanding something?
On the promising side, Opus doesn't look great at this benchmark either — maybe we can get better than Opus results by scaling this up. I guess that's the takeaway here.
Can someone please explain... If I don't know any Lean (and I suspect most people don't), is it of any direct value? Trying to understand if there's something it can help me with (e.g. automatically write proofs for my Go programs somehow... I'm not sure) or should I just cheer solely for more open models out there, but this one isn't for me?
I absolutely called this a couple of weeks ago, nice to be vindicated!
> I'm interested to see what it is in the age of LLMs or similar future tools. I suspect a future phase change might be towards disregarding how easy it is for humans to work with the code and instead focus on provability, testing, perhaps combined with token efficiency.
> Maybe Lean combined with Rust shrunk down to something that is very compiler friendly. Imagine if you could specify what you need in high level language and instead of getting back "vibe code", you get back proven correct code, because that's the only kind of code that will successfully compile.
Maybe a naive question: given that they see better performance with more passes but the effect hits a limit after a few passes, would performance increase if they used different models per pass, i.e leanstral, kimi, qwen and leanstral again instead of 4x leanstral?
Formal verification and code synthesis feel like natural companions for automated scientific discovery. I’ve been working on a small (~800‑line) Python agent that uses sparse regression to uncover governing equations directly from data; it’s managed to validate twelve physical laws, including deriving the Sun’s rotation rate from NASA plasma measurements and correcting Gemini’s plasma conservation. Having an agent like Leanstral that can reason about proofs and specifications would be a powerful complement to data‑driven model discovery — it closes the loop between experimentation and provable correctness.
Very cool but I haven’t been able to convince software developers in industry to write property based tests. I sometimes joke that we will start writing formal proofs until the tests improve. Just so that they will appreciate the difference a little more.
I can’t even convince most developers to use model checkers. Far more informal than a full proof in Lean. Still highly useful in many engineering tasks. People prefer boxes and arrows and waving their hands.
Anyway, I don’t know that I’d want to have a system vibe code a proof. These types of proofs, I suspect, aren’t going to be generated to be readable, elegant, and be well understood by people. Like programs they generate it will look plausible.
And besides, you will still need a human to review the proof and make sure it’s specifying the right things. This doesn’t solve that requirement.
Although I have thought that it would be useful to have a system that could prove trivial lemmas in the proof. That would be very neat.
I just feel like Mistral is heading for bad financial times when they are focusing on fringe academic areas and not on building a business out of their research. Initial Mistral was largely based on LLaMA, then they added innovative MoE and since then disappeared, doing AI consulting for big EU companies instead.
191 comments
TDD, verification, whatever your tool; verification suites of all sorts accrue over time into a very detailed repository of documentation of how things are supposed to work that, being executable, puts zero tokens in the context when the code is correct.
It’s more powerful than reams upon reams of markdown specs. That’s because it encodes details, not intent. Your intent is helpful at the leading edge of the process, but the codified result needs shoring up to prevent regression. That’s the area software engineering has always ignored because we have gotten by on letting teams hold context in their heads and docs.
As software gets more complex we need better solutions than “go ask Jim about that, bloke’s been in the code for years”.
> Instead of taking a stab in the dark, Leanstral rolled up its sleeves. It successfully built test code to recreate the failing environment and diagnosed the underlying issue with definitional equality. The model correctly identified that because def creates a rigid definition requiring explicit unfolding, it was actively blocking the rw tactic from seeing the underlying structure it needed to match.
Many comments here point out that Mistral's models are not keeping up with other frontier models - this has been my personal experience as well. However, we need more diversity of model alignment techniques and companies training them - so any company taking this seriously is valuable.
Europeans not wanting to be dependent, and they are giving for free what US investors planed to charge with 90% margin.
Amazing! What a blast. Thank you for your service (this first 100M$ burned to POC GPT1 and from here, we are so good to go)
This model is specifically trained on this task and significantly[1] underperforms opus.
Opus costs about 6x more.
Which seems... totally worth it based on the task at hand.
[1]: based on the total spread of tested models
Not sure I really understand the comparisons though. They emphasize the cost savings relative to Haiku, but Haiku kinda sucks at this task, and Leanstral is worse? If you're optimizing for correctness, why would "yeah it sucks but it's 10 times cheaper" be relevant? Or am I misunderstanding something?
On the promising side, Opus doesn't look great at this benchmark either — maybe we can get better than Opus results by scaling this up. I guess that's the takeaway here.
> I'm interested to see what it is in the age of LLMs or similar future tools. I suspect a future phase change might be towards disregarding how easy it is for humans to work with the code and instead focus on provability, testing, perhaps combined with token efficiency.
> Maybe Lean combined with Rust shrunk down to something that is very compiler friendly. Imagine if you could specify what you need in high level language and instead of getting back "vibe code", you get back proven correct code, because that's the only kind of code that will successfully compile.
https://news.ycombinator.com/item?id=47192116
I can’t even convince most developers to use model checkers. Far more informal than a full proof in Lean. Still highly useful in many engineering tasks. People prefer boxes and arrows and waving their hands.
Anyway, I don’t know that I’d want to have a system vibe code a proof. These types of proofs, I suspect, aren’t going to be generated to be readable, elegant, and be well understood by people. Like programs they generate it will look plausible.
And besides, you will still need a human to review the proof and make sure it’s specifying the right things. This doesn’t solve that requirement.
Although I have thought that it would be useful to have a system that could prove trivial lemmas in the proof. That would be very neat.