AI Briefing#formal-verification
The latest AI and developer news about #formal-verification, with the original source and a short summary.
The latest AI and developer news about #formal-verification, with the original source and a short summary.
Anthropic has published the first fully mechanically verified proof of Fermat's Last Theorem using Claude.
MathKernel, a multi-engine math kernel that specifies mathematical evidence and verification levels, has been released to address the arithmetic weaknesses of LLMs.
Claude Code proved that the maximum number of lines for the 15-point Orchard Problem is 31, using SAT verification.
Claude autonomously formalized Fermat's Last Theorem in the Lean language in just 11 days, generating 13 million lines of code.
The Palomar registry, which registers and manages mathematically verified proofs in the Lean language, has been released.
Anthropic announced research results using AI agents to raise the lower bound of the proportion of zeros of the Riemann zeta function on the critical line to 67.25%.
LLM-powered automation is shortening the formal verification process, a core aspect of programming language research, and changing research culture.
Amazon's Automated Reasoning Group reflects on its past decade of research and achievements.
OpenAI's unreleased model Astra has produced new results on 10 open math problems.
Microsoft has unveiled a technique that leverages Rust, Aeneas, and Lean to verify the mathematical integrity of SymCrypt's cryptographic algorithms.
Leanstral 1.5, an open-source model based on Lean 4 specialized for Formal Verification, has been released.
Mistral AI released Leanstral 1.5, a Lean 4 model optimized for automated theorem proving and autoformalization.
AWS has introduced the Nitro Isolation Engine, which guarantees isolation between virtual machines through mathematical proof, as the first such deployment in commercial cloud.
A tool has been released that enforces invariants in AI-generated code through formal verification
The FormalSLT library, which mechanically verifies proofs in statistical learning theory using Lean 4, has been released.
This summarizes Ada's design philosophy and its influence on modern languages.
AWS formally verified the security and correctness of the Nitro Isolation Engine using Isabelle/HOL.
Fuzzing of Lean-verified code uncovered a runtime overflow and a DoS vulnerability.
105M fuzzing runs uncovered a Lean runtime heap overflow and a lean-zip DoS.
Amazon achieved a high-performance, high-assurance implementation of ML-KEM through formal verification and optimization.
Arm64 AES-256-XTS was verified with HOL Light and added to s2n-bignum.
Leanstral, the first open-source code agent for Lean 4, has been released with formal proof as a target as well.
AI speeds up mathematical proofs and paper writing, but it is shaking up education and peer review.
The core of AI agents lies not in flashy features but in the reliability of scrolling and clicking.