What is Hackers' Pub?

Show GN: MCP YouTube Intelligence — YouTube 영상을 토큰 | GeekNews

YouTube 자막을 서버에서 처리(요약/엔티티/토픽/감성분석)해서LLM 클라이언트에는 압축된 결과만 전달하는 MCP 서버입니다.만든 이유:기존 YouTube MCP 서버 약 80개를 조사해봤는데, 전부 원본 자막을그대로 LLM에 던집니다. 20분 영상 하나에 ~15,000 토큰이소모되는 걸 요약 ~200-500 토큰, 전체 리포트도 ~3,000 토큰으로줄

news.hada.io · GeekNews

Towards Term-based Verification of Diagrammatic Equivalence

A string diagram is a two-dimensional graphical representation that can be described as a one-dimensional term generated from a set of primitives using sequential and parallel compositions. Since different syntactic terms may represent the same diagram, this syntax is quotiented by a collection of coherence equations expressing equivalence up to deformation. This work lays foundations for automated reasoning about diagrammatic equivalence, motivated primarily by the verification of quantum circuit equivalences. We consider two classes of diagrams, for which we introduce normalizing term rewriting systems that equate diagrammatically equivalent terms. In both cases, we prove termination and confluence with the help of the proof assistant Isabelle/HOL.

arxiv.org · arXiv.org

Query-based compiler architectures | Olle Fredriksson's blog

What a query-based compiler is and what they are good for.

ollef.github.io

reference-global.com

bee (@zynaesthesie@mastodon.social)

#Merz könnte sich seinen Job als Aushilfsdiktator viel einfacher machen, indem er sagt, dass er alle Deutschen hasst und von ihnen erwartet, dass sie ihn bezahlen, wenn sie ein Recht auf Leben haben wollen

mastodon.social · Mastodon

Analysis of reported issues in vodozemac

Matrix, the open protocol for secure decentralised communications

matrix.org

ISMバンド - Wikipedia

ja.wikipedia.org

Towards Real-World Industrial-Scale Verification: LLM-Driven Theorem Proving on seL4

Formal methods (FM) are reliable but costly to apply, often requiring years of expert effort in industrial-scale projects such as seL4, especially for theorem proving. Recent advances in large language models (LLMs) have made automated theorem proving increasingly feasible. However, most prior work focuses on mathematics-oriented benchmarks such as miniF2F, with limited evaluation on real-world verification projects. The few studies that consider industrial-scale verification mostly rely on closed-source models with hundreds of billions of parameters, which cannot be locally deployed and incur substantial usage costs. In this paper, we propose AutoReal, an LLM-driven theorem proving method for real-world industrial-scale systems with support for lightweight local deployment. We evaluate AutoReal on the seL4-Isabelle verification project as a representative and challenging case study. AutoReal incorporates two key improvements: (1) chain-of-thought (CoT)-based proof training, which teaches the LLM the reasoning behind proof steps and enables step-wise explanations alongside proofs, and (2) context augmentation, which leverages proof context from the project to enhance LLM-driven proving. Based on the AutoReal methodology, we fine-tune a base model to obtain AutoReal-Prover, a compact 7B-scale prover for industrial-scale theorem proving. AutoReal-Prover achieves a 51.67% proof success rate on 660 theorems from seL4-designated Important Theories across all 10 seL4 proof categories, substantially outperforming prior attempts on seL4 (27.06%). To evaluate generalization, we further apply AutoReal-Prover to three security-related projects from the Archive of Formal Proofs (AFP), covering all 451 theorems and achieving a proof success rate of 53.88%. Overall, this work advances the application of LLM-driven theorem proving in real-world industrial-scale verification.

arxiv.org · arXiv.org

How to Choose Between Hindley-Milner and Bidirectional Typing

A false dichotomy that hides the real request

thunderseethe.dev · Thunderseethe's Devlog

wasmtime-rb/ext/src/ruby_api/memory/unsafe_slice.rs at main · bytecodealliance/wasmtime-rb

Ruby WebAssembly runtime powered by Wasmtime. Contribute to bytecodealliance/wasmtime-rb development by creating an account on GitHub.

github.com · GitHub

bee (@zynaesthesie@mastodon.social)

#Merz könnte sich seinen Job als Aushilfsdiktator viel einfacher machen, indem er sagt, dass er alle Deutschen hasst und von ihnen erwartet, dass sie ihn bezahlen, wenn sie ein Recht auf Leben haben wollen

mastodon.social · Mastodon