Sequent retweeted
The finders of the new Lean soundness bug have unveiled their manifesto 👀
Please read our article, "Why Higher-Order Logic Is a Good Foundation for Deep Verification", authored by Ramana Kumar and Charles Cooper!
xitter.gq/Sequent_Inc/status/208…
Please read our article, "Why Higher-Order Logic Is a Good Foundation for Deep Verification", authored by Ramana Kumar and Charles Cooper!
xitter.gq/Sequent_Inc/status/208…
Shoutouts to Ramana Kumar for refuting the Collatz Conjecture in Lean, *as checked by Comparator!* github.com/xrchz/CollatzLean…
Sequent retweeted
Shoutouts to Ramana Kumar for refuting the Collatz Conjecture in Lean, *as checked by Comparator!* github.com/xrchz/CollatzLean…
We are excited to announce that we are working with @CurveFinance to formally verify LP safety for 2-coin StableSwap!
These are machine-checked mathematical proofs in higher order logic, not an audit.
First proofs are green, with more in the pipeline! 🧵 1/
And the goal is that you don't have to trust us. The proofs are artifacts! When the work wraps, you'll be able to re-run the checker yourself and watch it go green. 7/
Sequent retweeted
We’re changing our name: Sequent is now Resolution.
🧵
Sequent retweeted
"With @Sequent_Inc, teams spend less time proving that core invariants hold and more time on the questions a proof cannot answer: what correctness means, and what users actually care about"
sequent.inc/blog/posts/limit…
The @vyperlang team was Project Odin's first participant:
Sequent retweeted
I see four outcomes for all of these formal verification and "formalization" startups:
1.) They are forced to go vertical because formalization alone without a target market means nothing.
2.) They realize that teaching an LLM to write strong formal specifications under Hoare logic for code is the same thing as teaching an LLM to write good code. A strong spec for the code ends up being the code.
3.) They end up realizing that verifying a slop proof in LEAN no way improves the proof.
4.) They ultimately evolve into a neurosymbolic AI research lab and embrace property-based testing to pursue actual intelligence.
Today, I'm thrilled to announce Pramaana's $27M seed, led by @khoslaventures.
The foundational domains that hold the world together: tax, law, finance, healthcare; all run on certainty. Probabilistic AI can't give them that. We’ve been asked to accept wrong answers with AI as ‘hallucinations’, while in traditional software terms, it’s just a bug. And a wrong answer in such mission-critical domains is more than just a bug, it's a liability that could have catastrophic impact.
We built Pramaana to deliver a 100% trustable experience to the domains that run on certainty: AI that is provably correct, not probabilistically correct. We turn statute and regulation into machine-verifiable code, so every output ships with mathematical proof of correctness. Our mission is to make AI take ownership of it’s work.
Pramaana in Sanskrit stands for “means of valid knowledge”, and we’re going to achieve that by formalizing the world’s knowledge.
Formatted article with links on our blog: sequent.inc/blog/posts/ai-cy…
Sequent retweeted
A big part of that acceleration comes from early access to @Sequent_Inc's Alan, a state-of-the-art AI-powered prover agent which performs autonomous proving and also assists with specification modeling and theorem generation
