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

P
Palo Alto Networks Blog
大猫的无限游戏
大猫的无限游戏
Martin Fowler
Martin Fowler
GbyAI
GbyAI
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
量子位
T
The Blog of Author Tim Ferriss
Y
Y Combinator Blog
Microsoft Azure Blog
Microsoft Azure Blog
C
CERT Recently Published Vulnerability Notes
Recent Announcements
Recent Announcements
A
About on SuperTechFans
aimingoo的专栏
aimingoo的专栏
P
Privacy International News Feed
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
博客园 - 叶小钗
L
Lohrmann on Cybersecurity
G
GRAHAM CLULEY
T
The Exploit Database - CXSecurity.com
Hugging Face - Blog
Hugging Face - Blog
P
Proofpoint News Feed
NISL@THU
NISL@THU
博客园 - Franky
C
Cybersecurity and Infrastructure Security Agency CISA
The Register - Security
The Register - Security
M
MIT News - Artificial intelligence
Know Your Adversary
Know Your Adversary
A
Arctic Wolf
F
Full Disclosure
T
Threat Research - Cisco Blogs
P
Privacy & Cybersecurity Law Blog
The Hacker News
The Hacker News
博客园 - 【当耐特】
D
Docker
T
Tailwind CSS Blog
S
SegmentFault 最新的问题
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Jina AI
Jina AI
Help Net Security
Help Net Security
V
Visual Studio Blog
小众软件
小众软件
B
Blog
Vercel News
Vercel News
云风的 BLOG
云风的 BLOG
N
News and Events Feed by Topic
Forbes - Security
Forbes - Security
N
Netflix TechBlog - Medium
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
C
Cisco Blogs
Security Archives - TechRepublic
Security Archives - TechRepublic

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
RFC BBOS-RAU-0001 — BlueBookOS: Thee GPT Microkernel™
logn · 2026-06-27 · via Hacker News - Newest: "LLM"

Live Sandbox / REPL

Try BlueBookOS in ChatGPT.

Open the GPT that runs this page’s BlueBookOS microkernel, then ask it to build a source-first RAu artifact in a live chat sandbox.

Launch Sandbox / REPL

Two installation options

Pick your paste.

Two installation options. Both buttons copy a complete BlueBookOS boot packet. Pick the version that best matches the AI model you're using.

What is this See what it can make

Jailbreak More permissive boot packet for models that accept it.
Safe Compatibility-focused boot packet for stricter chats.

Showing Safe · compatibility-focused boot packet.

Loading selected copy-pasta…

A tiny OS for making apps with AI

BlueBookOS
boots in your chat.

BlueBookOS is a small set of rules and source code you paste into another AI chat. It helps that chat build apps carefully: first the RAu contract, then the working file. RAu is the little instruction language inside it. You can start without knowing either one.

Install it See the demos

5Demos included

Source lines

Built lines

0Installs needed

1. Abstract

This document specifies a practical artifact packaging pattern for BlueBookOS: Thee GPT Microkernel™, Powered by RAu.

RAu is used here as a source-first artifact contract. The HTML5 files are host ports that render the behavior described by the RAu source. This app is intentionally plain to operate: open it, open the demo, inspect the final RAu, inspect the final HTML, and run the rendered page in place.

The main product claim is simple: a good AI artifact should not only be impressive to view; it should be reusable, reviewable, copyable, and portable into the next project.

2. Status of This Memo

This is a readable product-facing draft, written in an RFC style without burying the point in ceremony.

The key words MUST, SHOULD, and MAY are used in their everyday standards-document sense: MUST means required for this showcase pattern, SHOULD means recommended for most projects, and MAY means optional but supported.

This file is self-contained. It does not require a server, package manager, build pipeline, remote stylesheet, CDN, or network call.

3. Terminology

These terms keep the spec readable while preserving the source-first model.

RAu

The programming language and runtime used as the semantic source contract for an artifact.

Artifact

A complete app, game, editor, reader, visualizer, or workflow unit intended to be shipped or remixed.

Host Port

The executable target implementation. In this package, every host port is standalone HTML5.

Rendered Page

The live browser view generated by loading the final HTML port into an embedded frame.

Source-First

The RAu contract is treated as the durable product definition before host-language changes are made.

Vibe Coding

A fast builder workflow where a human steers a frontier model with complete artifacts, clear goals, and acceptance criteria.

4. Artifact Packaging Specification

The showcase exposes just the pieces a builder needs: final examples, final RAu, final HTML, and live rendered output.

The package MUST embed the demo locally.
No runtime fetch is required to inspect source or render the included pages.

The demo MUST expose final RAu.
The RAu view is the artifact contract a model or human can reason about before changing the host implementation.

The demo MUST expose final HTML5.
The HTML view is the copyable, shippable browser port derived from the source-first artifact.

Each example MUST render inside the app.
The rendered page view makes the spec demonstrable without leaving the document.

The app SHOULD be usable as a model prompt payload.
A builder should be able to paste this entire file into a frontier model and ask for a new artifact, a refactor, a port, or a new catalog entry.

The app MAY be extended with new examples.
Additional RAu/HTML pairs can follow the same pattern: source contract, host port, metadata, rendered preview.

5. Reference Architecture

RAu remains the durable product contract; HTML5 is the executable browser delivery format.

The reference flow is intentionally lightweight. It works for games, editors, readers, canvas tools, dashboards, simulations, prompt packets, and other generated artifacts.

1State the intent

Name the artifact, user controls, data model, render targets, and success conditions.

2Write the RAu

Use RAu as the product contract for behavior, guards, events, and rendering.

3Derive HTML5

Generate a standalone browser port with complete input and render behavior.

4Ship and remix

Run the page, copy the source, modify the contract, and reuse the pattern.

6. Example Catalog

Select an artifact to inspect its final RAu, generated output, and live preview.

Loading…

Preparing embedded artifacts.

7. Vibe Coders Guide

Use the large prompt at the top of this page to request a new source-first RAu artifact.

Recommended workflow: copy the large prompt at the top, replace the bracketed goal with the app you want, and ask the model to return the RAu contract before the standalone HTML5 file. Use the examples below as references for how the source-first pattern should look.

Start with the prompt.

Do not rely on screenshots. The useful pattern is the source-first contract followed by a working standalone host port.

Give one concrete target.

Examples: “make a calendar app,” “derive a puzzle game,” “port this into a todo tool,” or “add another example.”

Ask for RAu first, then HTML5.

Preserve the source-first rule: update or derive the RAu contract before changing the host port.

Demand a standalone output.

Require a single HTML5 file with no build step, no CDN, and no runtime network dependency unless explicitly intended.

Use acceptance checks.

Ask the model to list controls, expected behaviors, edge cases, and what changed from the original examples.

Best for

Rapid prototypes, client demos, internal tools, interactive specs, game mechanics, UI experiments, and product pitches.

Model input

The full HTML file plus a clear instruction: extract the RAu/HTML pattern and generate the next artifact.

Model output

A revised RAu contract and a complete standalone HTML5 app, ready to save as a local file and run.

8. Copy-Paste Prompts

Use these prompts with the copied HTML app to guide a frontier model toward useful, shippable output.

Prompt A · New artifact from this packet

Prompt B · Refactor or extend the demo

9. Conformance Checklist

A new BlueBookOS / RAu showcase entry conforms to this spec when it satisfies these checks.

Branding is intact.

The artifact is clearly branded as BlueBookOS: Thee GPT Microkernel™ and Powered by RAu.

RAu is visible.

The final RAu source can be inspected and copied without a build step.

HTML5 is visible.

The final standalone host port can be inspected, copied, downloaded, and opened.

Rendered page works locally.

The preview runs with local embedded source and does not depend on remote assets.

Future builders can reuse it.

The package includes enough context for a human or model to derive another artifact from the pattern.