惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

K
Kaspersky official blog
G
Google Developers Blog
Apple Machine Learning Research
Apple Machine Learning Research
V
Visual Studio Blog
WordPress大学
WordPress大学
博客园 - Franky
雷峰网
雷峰网
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
博客园 - 【当耐特】
人人都是产品经理
人人都是产品经理
月光博客
月光博客
V
V2EX
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
IT之家
IT之家
小众软件
小众软件
Cloudbric
Cloudbric
量子位
N
News and Events Feed by Topic
Vercel News
Vercel News
Security Archives - TechRepublic
Security Archives - TechRepublic
www.infosecurity-magazine.com
www.infosecurity-magazine.com
C
Check Point Blog
The Cloudflare Blog
Hugging Face - Blog
Hugging Face - Blog
T
Tenable Blog
S
Secure Thoughts
Know Your Adversary
Know Your Adversary
C
CXSECURITY Database RSS Feed - CXSecurity.com
C
Cyber Attacks, Cyber Crime and Cyber Security
Stack Overflow Blog
Stack Overflow Blog
Help Net Security
Help Net Security
L
LINUX DO - 最新话题
Google DeepMind News
Google DeepMind News
云风的 BLOG
云风的 BLOG
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
N
News | PayPal Newsroom
PCI Perspectives
PCI Perspectives
T
Troy Hunt's Blog
GbyAI
GbyAI
Attack and Defense Labs
Attack and Defense Labs
C
Cybersecurity and Infrastructure Security Agency CISA
Y
Y Combinator Blog
美团技术团队
爱范儿
爱范儿
Martin Fowler
Martin Fowler
Last Week in AI
Last Week in AI
P
Privacy International News Feed
T
The Blog of Author Tim Ferriss
F
Full Disclosure

Hacker News - Newest: "LLM"

GitHub - lechmazur/position_bias: A benchmark for testing whether LLM judges keep the same preference when two lightly edited versions of the same story are shown in opposite orders. Flex routing (EU and EFTA) Dark Factories: Retooling for LLM Velocity Ask HN: What would be the impact of a LLM output injection attack? GitHub - AronDaron/dataset-generator: No-code desktop app for generating high-quality synthetic datasets to fine-tune LLMs — plan-then-execute pipeline, LLM-as-judge, HuggingFace upload. GitHub - Oaklight/llm-rosetta: Production-ready LLM API translation layer for Python — bidirectional conversion between OpenAI, Anthropic & Google formats via hub-and-spoke IR. Optional API gateway. Streaming & non-streaming. Zero core deps. Contributions welcome! GitHub - browser-use/browser-harness: Self-healing browser harness that enables LLMs to complete any task. GitHub - moeen-mahmud/remen: Remen turns thoughts into something you can return to Analyzing 156 LLM Launch Posts on Hacker News ChatGPT vs Gemini vs Claude: The Best LLM Subscription You Should Buy GitHub - salaamalykum/quran-semantic-search: High-density RAG Semantic Search Engine & Quran Corpus (GEO/SEO Architecture) GitHub - NVIDIA/TensorRT-LLM: TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way. The State of LLM Bug Bounties in 2026 Operational Readiness Criteria for Tool-Using LLM Agents Meshcore: Architecture for a Decentralized P2P LLM Inference Network How an LLM becomes more coherent as we train it GitHub - seetrex-ai/laimark GitHub - Jossifresben/BibCrit: AI-assited biblical textual criticism GitHub - wastedcode/memex: File system based wiki, maintained by Claude 99helpers.com GitHub - cliver-project/AITrigram GitHub - unbody-io/adapt: A self-evolving memory layer for AI agents. GitHub - hb20007/awesome-gen-ai-fails: A list of incidents where reliance on generative AI and LLMs resulted in harm to companies, individuals, or society GitHub - nevenkordic/localmind: Run any local LLM with persistent memory and context. CLI agent over Ollama with SQLite-backed hybrid recall. No cloud. Ask HN: What are the machine requirements for a LLM like Llama-3.1-8B? Faster LLM Inference via Sequential Monte Carlo grpo explained: group relative policy optimization for llm finetuning - cgft Stop comparing price per million tokens: the hidden LLM API costs · TensorZero Andrej Karpathy's LLM Wiki Is a Bad Idea GitHub - GG-QandV/mnemostroma: Offline RAM-first cognitive leer/coprocessor for AI agents and robotics. Solves "Context Abandonment" with 20-80ms latency using a dual-thread biomimetic memory architecture (ONNX + SQLite WAL). mempalace/agent at agent · skorotkiewicz/mempalace GitHub - Nyquest-ai/nyquest-rust-fullstack-pub: Nyquest — Semantic Compression Proxy for LLMs. 350+ rules, local LLM stage, 15-75% token savings. Full Rust stack. GitHub - TheoV823/mneme: Enforce architectural decisions in AI-assisted development. GitHub - klemenvod/TokenBrawl: A 1v1 Bomberman-style game where two LLM agents play autonomously against each other. No human plays — you watch the AIs fight. Each agent receives a text description of the board state, reasons about it, and outputs a move as JSON. The game engine executes it. Introducing the Common AI Provider: LLM and AI Agent Support for Apache Airflow Power Circuit AI: Designing Power Electronic Circuits for Motor Drives with Generative Artificial Intelligence Ask HN: How to program with IDE and LLM on CPU locally? Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis Bonsai 1-bit WebGPU - a Hugging Face Space by webml-community The LLM Fallacy: Misattribution in AI-Assisted Cognitive Workflows Ask HN: Simple tooling for local LLM code critique without IDE integration? Can a General LLM Diagnose a DICOM Slice? A 10-Case Public Benchmark Charts-of-Thought: Enhancing LLM Visualization Literacy (PDF, 2026) GitHub - Mesh-LLM/mesh-llm: Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat. GitHub - seamus-brady/springdrift: A persistent runtime for long-lived LLM agents Writing an LLM from scratch, part 32k -- Interventions: training a better model locally with gradient accumulation Ask HN: Which LLM model and agentic CLI are you using for local development? GitHub - wayneColt/modelcascade: Route local. Escalate smart. Never overspend. Open-source multi-model cascade routing for autonomous agents. LLM pricing is 100x harder than you think GitHub - asakin/llm-primer: Pre-warmed Claude Code sessions in tmux. No startup wait. GitHub - EggerMarc/chat-rs: A multi-provider LLM framework for Rust. GitHub - SynapseKit/SynapseKit: Minimal, async-first Python framework for production LLM apps- 2 hard deps, no magic, no SaaS. A Claude Skill that Makes LLM Paragraphs More Bearable Does Gas Town 'steal' usage from users' LLM credits & paid services to improve itself? What's Claude Code Actually Doing? Open the Black Box with the Arthur Engine Milla Jovovich's New Open Source LLM Memory App and the Dark Code Problem Your intuition of LLM token usage might be wrong Show HN: Bloomberg Terminal for LLM ops – free and open source GitHub - 0xchamin/mcptube: Transform YouTube videos into a compounding knowledge base with transcripts, vision analysis, and agentic search. Works as an MCP server for Claude, Copilot & more. Show HN: Open KB: Open LLM Knowledge Base Your LLM is a compiler, not a runtime GitHub - sapountzis/Unslop: A Web Feed That Deserves You crates.io: Rust Package Registry Beyond Karpathy's LLM-Wiki: The Necessity of Cognitive Governance GitHub - amitshekhariitbhu/llm-internals: Learn LLM internals step by step - from tokenization to attention to inference optimization. GitHub - parallem-ai/parallem: An expressive library for running agents with the Batch API. GitHub - stfurkan/pi-llm LLM-Wiki Show HN: Formal – Formal verification for AI-generated code using Lean 4 LRTS – Regression testing for LLM prompts (open source, local-first) LLM Wiki Skill: Build a Second Brain with Claude Code and Obsidian I built an LLM Wiki and RAG solution: here's a demo for a security KB The biggest advance in AI since the LLM Predict-Rlm: The LLM Runtime That Lets Models Write Their Own Control Flow the-synthetic-library/the-synthetic-mind at main · joshferrer1/the-synthetic-library GitHub - yisding/reviewwiggum GitHub - Donnyb369/mcp-spine: Context Minifier & State Guard — Local-first MCP middleware proxy GitHub - Beledarian/wgpu-llm: A from-scratch LLM inference engine that uses wgpu (the cross-platform WebGPU implementation) to dispatch WGSL compute shaders for every math operation a Transformer needs. No CUDA. No Python. No massive framework dependencies. Just Rust, raw shaders, and your GPU. GitHub - anitiue/Hindsight: An experience-driven self-improvement framework for LLM agents — 基于经验的 LLM Agent 自我改进框架 GitHub - stef41/lmscan: 🔍 Detect AI-generated text and fingerprint which LLM wrote it. Open-source GPTZero alternative. Zero dependencies, works offline. GitHub - alainnothere/AmdPerformanceTesting: Amd Performance Testing Ask HN: Is a purely Markdown-based CRM a terrible idea? Optimized for LLM agents Context Engineering - LLM Memory and Retrieval for AI Agents | Weaviate little_helper_tui/letter.md at main · sleepyeldrazi/little_helper_tui GitHub - EvanZhouDev/umr: The Unified Model Registry for all your local AI apps. GitHub - JordanCT/VigIA-Orchestrator Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain A Taxonomy of RL Environments for LLM Agents Llama LLM Network Feture GitHub - genedeng-ca/ai-mac-migration: AI-powered Mac-to-Mac migration tool - replace Apple Migration Assistant with intelligent, selective transfer using local LLMs GitHub - lunargate-ai/gateway: High-performance self-hosted AI gateway (OpenAI-compatible) with routing, retries, and streaming GitHub - AuthBits/webmcp: A lightweight, prompt-driven MCP web research server for high-quality LLM powered information extraction. Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering Springdrift: An Auditable Persistent Runtime for LLM Agents with Case-Based Memory, Normative Safety, and Ambient Self-Perception High-Stakes Personalization: Rethinking LLM Customization for Individual Investor Decision-Making From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents HUOZIIME: An On-Device LLM-enhanced Input Method for Deep Personalization TIDE: Token-Informed Depth Execution for Per-Token Early Exit in LLM Inference Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users
GitHub - thisismydesign/okf-lint: A linter for the Open Knowledge Format (OKF)
thisismydesi · 2026-06-23 · via Hacker News - Newest: "LLM"

A linter for the Open Knowledge Format (OKF) — Google's open, human- and agent-friendly format for knowledge catalogs.

Think of it as ESLint or RuboCop, but for OKF bundles. okf-lint:

  • Reports errors when a bundle violates a mandatory OKF conformance requirement (e.g. a concept document is missing its type field).
  • Reports warnings when a bundle skips an optional-but-useful convention (e.g. no index.md, no log.md, or a concept document without a description).

The OKF version is selected per bundle. Supported versions: 0.1. If a bundle does not specify a version, or specifies one the linter does not support, the highest supported version is used.

Specification: https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md


Installation

# one-off, no install
pnpm dlx @thisismydesign/okf-lint ./my-bundle

# or add it to a project
pnpm add -D @thisismydesign/okf-lint

This package is published as @thisismydesign/okf-lint. It targets Node.js ≥ 18 and ships as ESM.

Usage (CLI)

Point it at a bundle directory (the folder that contains your OKF markdown files):

okf-lint ./path/to/bundle
./path/to/bundle/tables/customer-metrics.md
  7:1      warning  Missing recommended `description` field (a one-line summary).  recommended-description

✖ 1 problem (0 errors, 1 warning)

Options

Option Description
path Path to the OKF bundle directory (default: .).
-f, --format <fmt> Output format: stylish (default) or json.
-q, --quiet Report errors only (suppress warnings).
--max-warnings <n> Exit non-zero if the number of warnings exceeds <n>.
--list-rules Print every rule for the latest version and exit.
-v, --version Print the okf-lint version and exit.
-h, --help Show help and exit.

Exit codes

Code Meaning
0 No errors (and warnings within --max-warnings, if set).
1 Errors found, or warnings exceeded --max-warnings.
2 Usage or runtime error (bad option, unreadable path, …).

This makes it CI-friendly:

# fail the build on any error, but tolerate warnings
okf-lint ./bundle

# treat the bundle as a strict, zero-warning catalog
okf-lint ./bundle --max-warnings 0

Usage (programmatic)

import { lint, formatStylish } from '@thisismydesign/okf-lint';

const result = lint('./path/to/bundle');

console.log(result.errorCount, result.warningCount);
for (const d of result.diagnostics) {
  console.log(`${d.severity} ${d.ruleId} ${d.filePath}:${d.line}${d.message}`);
}

// or render the same human-readable report the CLI prints
console.log(formatStylish(result));

lint(target, options) returns:

interface LintResult {
  diagnostics: Diagnostic[]; // sorted by file, then line/column
  errorCount: number;
  warningCount: number;
  version: ResolvedVersion; // which OKF version was used, and why
}

You can pass inline configuration to override rule severities:

lint('./bundle', { config: { rules: { 'recommended-log': 'off' } } });

What it checks

OKF v0.1 models a bundle: a hierarchical directory of markdown files. Each non-reserved .md file is a concept document (YAML frontmatter + markdown body). Two filenames are reserved: index.md (a navigable listing) and log.md (an update history).

okf-lint is opinionated: the spec says a bundle is conformant with very few requirements, and that consumers should tolerate almost everything else. We honor that split exactly — only true conformance failures are errors; everything we merely recommend is a warning you can turn off.

Errors — mandatory OKF conformance

These map directly to the spec's conformance requirements. A bundle that produces any of these is not a conformant OKF v0.1 bundle.

Rule What it enforces
frontmatter-present Every non-reserved .md file begins with a YAML frontmatter block.
frontmatter-parseable That frontmatter block is parseable YAML (a mapping).
type-required Every frontmatter block has a non-empty type field.
index-frontmatter Only the bundle-root index.md may contain frontmatter; other index.md files must not.
index-version-key The bundle-root index.md frontmatter contains only okf_version.
log-date-format log.md entry headings use ISO 8601 YYYY-MM-DD dates.

Warnings — optional but useful (the opinionated part)

The spec marks these as optional, and forbids consumers from rejecting a bundle over them. But they make a catalog dramatically more useful to humans and agents, so okf-lint nudges you toward them. Disable any you disagree with.

Rule Why we recommend it
recommended-title A human-readable display name makes listings and search legible.
recommended-description A one-line summary is what most consumers show first.
recommended-timestamp A last-modified time lets consumers reason about freshness.
tags-type When present, tags should be a list of strings (not a bare scalar).
timestamp-format When present, timestamp should be a valid ISO 8601 datetime.
recommended-index A bundle-root index.md gives readers a navigable, grouped entry point.
recommended-log A log.md records how the catalog evolved — invaluable for consumers tracking changes.
log-date-order Log entries read best newest-first.
valid-links Internal .md cross-links should resolve. (The spec permits broken links; we flag them.)
prefer-absolute-links Bundle-absolute links (/path/to/doc.md) are more robust than relative ones.
okf-version-declared Declaring okf_version lets tools pick the right rules. (See Versioning.)
okf-version-supported Warns when the declared version is newer/unknown to this linter.
okf-version-format okf_version should be a quoted string so e.g. "0.10" isn't parsed as the number 0.1.

resource and tags are intentionally not required or recommended: many concepts have no underlying asset, and tags don't always make sense. When you do provide tags, tags-type checks that it's well-formed.

Run okf-lint --list-rules to print the full, current list.


Versioning

OKF uses <major>.<minor> versions. A bundle may declare the version it targets via okf_version in its bundle-root index.md frontmatter:

---
okf_version: '0.1'
---

# Tables

- [Customer Metrics](/tables/customer-metrics.md) - Aggregated daily KPIs.

okf-lint resolves which rule set to use as follows:

  1. Declared and supported → validate against that version.
  2. Declared but unsupported (e.g. a future 0.2) → emit an okf-version-supported warning and validate against the most recent supported version anyway (best-effort, as the spec recommends).
  3. Not declared → emit an okf-version-declared warning and validate against the most recent supported version.

The currently supported versions are listed by okf-lint --help. Today that is just 0.1.

Configuration

Drop a .okflintrc.json in your bundle root (or the directory you run okf-lint from) to tune rule severities. Each rule can be set to "error", "warning", or "off":

{
  "rules": {
    "recommended-timestamp": "off",
    "valid-links": "error",
    "okf-version-declared": "off"
  }
}

This is how you make the linter less or more opinionated for your catalog — turn off conventions you don't follow, or promote a warning to a hard error in CI.

Examples

The examples/ directory contains two runnable bundles:

  • examples/valid — a clean bundle that lints with zero problems.
  • examples/invalid — a bundle that intentionally triggers a representative spread of errors and warnings.
okf-lint examples/valid     # ✓ No problems found.
okf-lint examples/invalid   # ✖ 10 problems (4 errors, 6 warnings)

Development

This repo uses pnpm, TypeScript, ESLint, and Prettier.

pnpm install        # install dependencies
pnpm build          # compile TypeScript to dist/
pnpm test           # run the vitest suite
pnpm typecheck      # type-check without emitting
pnpm lint           # eslint
pnpm format         # prettier --write

Adding a new OKF version

  1. Create src/versions/v<major>_<minor>/rules.ts exporting a rules: Rule[] array (start by importing and adapting the v0.1 set).
  2. Register it in src/versions/index.ts (RULE_SETS and, when appropriate, LATEST_VERSION).
  3. Add fixtures under examples/ and assertions in test/.

Rules are small, self-contained objects (meta + run(context)), so most changes touch only one file.

License

MIT