We create products that ensure information and automation are trustworthy, accountable, and reliable. Building @predictablecode
Seattle / Cádiz
Joined February 2025
- Tweets51
- Following8
- Followers123
- Likes30
Predictable Machines retweeted
AI can write code faster than ever. But can it prove the code does what it is supposed to do?
At @Lambda_World, David Mazarro & Raúl Raja @raulraja from @AIPredictable ask exactly that in “Towards Multi-language Program Verification for AI”.
Generating software is becoming easy. TRUSTING it is hard.
29–30 Oct, 2026
Torremolinos, Malaga. Spain
#Lean4 #FormalMethods #AI #LambdaWorld
ALT Headshots from David and Raul and title of their talk
Predictable Machines retweeted
Maybe it's because I'm obsessed with the topic, but it feels like everyone in AI is suddenly talking about verification 🤓.
Not all verification is the same, though.
Most of what labs ship today is probabilistic: agents cross-checking each other, one model grading another's work. It scales to fuzzy, human problems, and honestly, it's the only thing that does. But you get confidence levels, never guarantees.
At @AIPredictable, we're betting on deterministic verification. Mathematical methods that give you a binary answer: does the code do what the spec says? Yes or no.
We generate specs, translate them into Lean, and formally verify every possible theorem about expected behavior. Not just the happy path.
It doesn't apply to everything. Ask it a philosophical question, and it's useless. But for code in banking, pharma, or healthcare, where "probably correct" doesn't cut it, the game changes.
So, honest question: is probabilistic verification enough for what you're building, or do you need the math?
Full story in @JYCabello's new article, production horror story included (a Friday deploy, a database index, and a two-week holiday):
predictablemachines.com/blog…
Worst bug a green CI ever hid from you?
That's why we went deterministic. No AI judging your code: LLMs are trained on decades of code full of the same implicit assumptions we've learned not to see.
We translate your logic into a Lean model and let the math emit the verdict. You keep writing in your language.
Your compiler trusts you. It shouldn't.
C# compiles a recursive loop that will slowly shove your database off a cliff. No warnings, no errors.
Lean refuses to compile the exact same logic until you prove it terminates. 🧵
We are at @seattlefloworg sharing what we’re building at @AIPredictable.
We'll be at the Startup Fair. Live demos of @predictablecode, great conversations, and a lot more coming soon ❤️
Back at Bell Harbor, but this time with a very different perspective.
We’re here at @seattlefloworg representing @AIPredictable and sharing a live demo of @predictablecode ❤️
That's how Predictable Code keeps AI-generated code aligned with what you actually specified. No surprises, no quiet deviations.
Full case study with the complete recording here:
predictablemachines.com/blog…
For every deviation between code and spec, three options:
→ Fix the code (scoped prompt, can't break other contracts)
→ Update the spec (if your intent was different)
→ Remove the spec (if it no longer applies)
This is the moment that matters 🤘
Syncs each requirement to the code that satisfies it, generates theorems, and proves them. Every theorem that doesn't hold comes back with the exact input that breaks it.
A local viewer to review every inferred contract before anything else runs.
If a requirement looks wrong or too strict, you correct it here first. The formal check will then run against the contract you actually want.
Step 1: @PredictableCode reads the codebase and infers the behavioral contracts that the code itself implies it should satisfy.
No specs written by hand. No annotations. Just the code and documentation, and what it formally promises to do.
The one question I keep coming back to with AI-generated code: does it actually do what I specified?
Our first @PredictableCode case study answers that end-to-end on a real Java codebase, with a full recording of the workflow.
predictablemachines.com/blog…
We'll be at @seattlefloworg Startup Day 2026 on May 15th, demoing @PredictableCode at the Startup Fair.
Come see what it looks like to formally verify AI-generated code. Not "passes review," actually proven correct. 👌
Tickets 👉 seattleflow.org/startupday
Predictable Machines retweeted
The last article of the #AICodePainPoints series is done! (For now, because every improvement in this field brings new issues with it.)
This time, it's about what happens when a developer clicks Merge on AI-generated code reviewed by another AI. What are they actually approving? And in regulated industries, who carries the weight when something breaks?
The accountability didn't disappear. It just concentrated in one click.
The final piece of our #AICodePainPoints series is up: the merge button and the weight it carries.
predictablemachines.com/blog…
AI writes the code.
AI reviews the code.
A developer clicks "merge" in under 10 minutes.
In that single click, all the legal and regulatory liability concentrates in one human, for code they didn't write and couldn't fully read.
Predictable Machines retweeted
Uno de los amigos que ayer hizo demo fue @Jorge__Galindo con su @AIPredictable .
Está escribiendo unos blogposts majos sobre cómo su bicho ayuda a solventar los pain points habituales de programar con IA, pero en su caso con clientes corporate para cosas serias (no el vibecodeo de pachanga que flexeamos por aquí).
Echadle un ojo, que merece la pena aprender sobre el curro que tiene el garantizar que tienes unas specs capaces de superar auditorías corporate, y no un markdown slopeado de esos...
predictablemachines.com/blog…
Predictable Machines retweeted
If you are curious about knowing the different pain points we see in the ai generated code, and how we think we can help, this series of articles could be interesting to you 😊
Documentation stopped being just for the team. It's now the context for every line of code your AI is about to write.
Third piece of our pain points series: predictablemachines.com/blog…
