MigGPT: AI-Powered Migration of Out‑of‑Tree Linux Kernel Patches

MigGPT, a new framework for out‑of‑tree Linux kernel patch migration, achieved a 74.07% completion rate on a real‑world benchmark, outperforming standard LLMs. Read more: getnews.me/miggpt-ai-powered-migrat... #linux #aiforcode

Real-time updates, syntax-aware chunking.
Production-ready. Ultra-performant. Fully #OpenSource.

#LLM #RAG #AIForCode #CodeSearch #DevTools #RealtimeAI #OpenSource #AIInfra #Rust #Python #TreeSitter #VectorDB #Embeddings #AIEngineering #GenerativeAI #Codex #CodingAgents #Claude #Cursor

Readings shared May 30, 2025 The readings shared in Bluesky on 30 May 2025 are Certified algorithms for numerical semigroups in Rocq. ~ Massimo Bartoletti, Stefano Bonzio, Marco Ferrara. #ITP #Rocq #Math Agent-based logics in de

Readings shared May 30, 2025. jaalonso.github.io/vestigium/po... #AIforCode #Agda #GenerativeAI #ITP #LeanProver #Math #Rocq

VERINA: Benchmarking Verifiable Code Generation Large language models (LLMs) are increasingly integrated in software development, but ensuring correctness in LLM-generated code remains challenging and often requires costly manual review. Verifiable...

VERINA: Benchmarking verifiable code generation. ~ Zhe Ye, Zhengxu Yan, Jingxuan He, Timothe Kasriel, Kaiyu Yang, Dawn Song. arxiv.org/abs/2505.23135 #AIforCode #ITP #LeanProver

Readings shared May 24, 2025 The readings shared in Bluesky on 24 May 2025 are A formal proof of complexity bounds on diophantine equations. ~ Jonas Bayer, Marco David. #ITP #IsabelleHOL #Math Munta: A verified model checker for

Readings shared May 24, 2025. jaalonso.github.io/vestigium/po... #AIforCode #FunctionalProgramming #Haskell #ITP #IsabelleHOL #Math #Physics

Is AI making coders obsolete? (Are there problems with having AI tools take over coding from humans?). ~ Jennifer Goforth Gregory. cacm.acm.org/news/is-ai-m... #AIforCode

Readings shared May 23, 2025 The readings shared in Bluesky on 23 May 2025 are A formal proof of complexity bounds on diophantine equations. ~ Jonas Bayer, Marco David. #ITP #IsabelleHOL #Math Solving guarded domain equations in

Readings shared May 23, 2025. jaalonso.github.io/vestigium/po... #AIforCode #CategoryTheory #ITP #IsabelleHOL #LLMs #LeanProver #Math #RocqProver

CLEVER: A Curated Benchmark for Formally Verified Code Generation We introduce ${\rm C{\small LEVER}}$, a high-quality, curated benchmark of 161 problems for end-to-end verified code generation in Lean. Each problem consists of (1) the task of generating a specifica...

CLEVER: A curated benchmark for formally verified code generation. ~ Amitayush Thakur et als. arxiv.org/abs/2505.139... #LLMs #ITP #LeanProver #AIforCode