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

aimingoo的专栏
aimingoo的专栏
Google DeepMind News
Google DeepMind News
S
SegmentFault 最新的问题
Project Zero
Project Zero
D
DataBreaches.Net
I
InfoQ
L
Lohrmann on Cybersecurity
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
酷 壳 – CoolShell
酷 壳 – CoolShell
Stack Overflow Blog
Stack Overflow Blog
The Register - Security
The Register - Security
Recorded Future
Recorded Future
Vercel News
Vercel News
博客园 - 司徒正美
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
I
Intezer
The Hacker News
The Hacker News
F
Fortinet All Blogs
Microsoft Azure Blog
Microsoft Azure Blog
P
Proofpoint News Feed
Help Net Security
Help Net Security
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
Application and Cybersecurity Blog
Application and Cybersecurity Blog
Scott Helme
Scott Helme
T
Threatpost
爱范儿
爱范儿
N
Netflix TechBlog - Medium
D
Docker
云风的 BLOG
云风的 BLOG
C
Cisco Blogs
K
Kaspersky official blog
H
Help Net Security
S
Secure Thoughts
T
Threat Research - Cisco Blogs
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
S
Security @ Cisco Blogs
Cyberwarzone
Cyberwarzone
N
News and Events Feed by Topic
G
Google Developers Blog
Forbes - Security
Forbes - Security
博客园 - 三生石上(FineUI控件)
博客园 - 叶小钗
B
Blog
Google DeepMind News
Google DeepMind News
Recent Announcements
Recent Announcements
Simon Willison's Weblog
Simon Willison's Weblog
S
Securelist
P
Privacy International News Feed
Spread Privacy
Spread Privacy
The Last Watchdog
The Last Watchdog

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 - Lucas2944/prpack: Pack a pull request into one markdown file optimized for LLM code review.
claudetester · 2026-05-11 · via Hacker News - Newest: "LLM"

release license GitHub Action Marketplace demo ko-fi

Pack a pull request into one markdown file optimized for LLM code review.

prpack

Try it without installing: paste a public GitHub PR URL into lucas2944.github.io/prpack-demo and watch the packed output appear in your browser. Pure client-side, no signup.

Looking for review prompts only? Lucas2944/prpack-prompts has four focused review prompts (security / performance / tests / architecture) as plain markdown files — append one to your context and you'll get structured reviews that catch real issues. Works with any LLM, with or without prpack.

Want this on every PR? See prpack-action — a GitHub Action wrapper. Drop a 5-line workflow in your repo and you get the packed markdown on every PR.

prpack walks the diff between two refs and emits a single, well-structured markdown file containing the commit list, the diff, and the full post-change contents of every touched file. Drop it into Claude / Cursor / any model and ask for review — no copy-pasting, no missing context, no per-file back-and-forth.

$ prpack --out ctx.md
prpack: base=origin/main head=HEAD merge-base=4f8a91c
prpack: 7 file(s) to pack (1 excluded)
prpack: wrote ctx.md (24.6 KB, ~6,150 tokens)

Then paste ctx.md into your model of choice and ask:

Review this PR. The diff and full file contents are below. Flag bugs, missing edge cases, and anything that would make a reviewer pause.

That's it.

Why

The technique behind prpack is written up at length in THE_TECHNIQUE.md — a story of how a missed null-deref taught me that LLM code review is a context-engineering problem, not a model problem. For a reproducible side-by-side, see examples/.

Asking an LLM to review a PR is the obvious move, but the context it sees matters more than the prompt. Just pasting a diff drops crucial context — the model can't see what the rest of the function looks like, how callers use the changed code, or what the surrounding module exports. Pasting the whole repo wastes tokens and dilutes attention.

prpack packs exactly the diff plus the full state of every file the diff touches. That's enough context to reason about the change without drowning the model in noise. If you want adjacent test files included automatically, pass --include-tests.

Install

# One-shot, no install:
npx github:Lucas2944/prpack --out ctx.md

# Or install globally:
npm install -g github:Lucas2944/prpack
prpack --out ctx.md

Requires Node 18+ and git on PATH.

Usage

prpack [options]

Options:
  --base <ref>          Base ref to diff against (default: origin/main, falls back to main)
  --head <ref>          Head ref (default: HEAD)
  --out <path>          Output file (default: stdout)
  --config <path>       Load preset from a .prpack.yml file
  --include-tests       Include test files even if not changed (auto-discovers siblings)
  --include-untracked   Include untracked files in the diff
  --no-content          Only include the diff, not full file contents
  --max-bytes <n>       Skip files larger than n bytes (default: 200000)
  --exclude <glob>      Exclude paths matching glob (repeatable)
  --review [angle]      Call Anthropic for a streamed review (default: general)
  --api-key <key>       Anthropic API key (overrides ANTHROPIC_API_KEY)
  --model <id>          Anthropic model for --review
  --yes                 Skip cost-estimate confirmation in TTY review mode
  --quiet               Suppress stderr progress logs

Review mode

One-line install plus review:

npx github:Lucas2944/prpack --review security --api-key "$ANTHROPIC_API_KEY"

--review packs the PR context, appends a focused review prompt, calls Anthropic's Messages API, and streams the response to your terminal. If you also pass --out ctx.md, prpack writes the packed context to ctx.md and the model's review to ctx.md.review.md.

Focused angles:

  • security
  • performance
  • tests
  • architecture

The default general angle gives a balanced pass across all four.

Common recipes

# Default: pack vs origin/main, write to ctx.md
prpack --out ctx.md

# Diff against a different base
prpack --base develop --out ctx.md

# Pack the last 3 commits even on main
prpack --base HEAD~3 --head HEAD --out ctx.md

# Diff-only, skip full contents (smaller, faster)
prpack --no-content --out ctx.md

# Pull adjacent tests in too
prpack --include-tests --out ctx.md

# Exclude generated/lock files
prpack --exclude 'pnpm-lock.yaml' --exclude 'dist/**' --out ctx.md

# Pipe straight to clipboard (macOS)
prpack | pbcopy

# Use a review preset (see prpack-pro)
prpack --config security.prpack.yml --out audit.md

# Stream a native AI review with the default general angle
prpack --review --yes

.prpack.yml configs

Drop a YAML file with any of these keys:

base: develop
includeTests: true
exclude:
  - dist/**
  - "*.lock"
preface: |
  This PR introduces a new payment flow. Focus on input validation and
  error paths around the Stripe webhook handler.
reviewPrompt: |
  You are a senior engineer reviewing this PR. Flag bugs, missing edge
  cases, and security issues. Quote line numbers when you do.

preface is added under "Reviewer note from author" near the top. reviewPrompt is appended at the end, ready for the model to act on.

For editor autocomplete and validation, add a # yaml-language-server line at the top of your config:

# yaml-language-server: $schema=https://raw.githubusercontent.com/Lucas2944/prpack/main/schema/prpack.schema.json
base: develop
includeTests: true

Output shape

# Pull Request Context
**Repo:** `org/repo`
**Branch:** `feature/...`
**Base:** `main` → **Head:** `HEAD`
**Commits:** 3
**Files changed:** 7

## Commits
- `abc1234` 2026-05-10 — Add Stripe webhook handler

## Files changed
- `src/payments/webhook.ts` _(added)_
- ...

---
## `src/payments/webhook.ts` _(added)_

### Diff
```diff
...

Full content (post-change)


Every code block uses a fence longer than any backtick run inside it, so embedded markdown / code samples never break formatting.

## What it doesn't do

- **No network calls in pack mode.** `prpack` only calls Anthropic when you explicitly pass `--review`.
- **No hidden AI.** Review mode uses your Anthropic API key and prints the cost estimate before the call.
- **No web UI.** It's a single CLI binary.
- **No telemetry.** Pack mode never opens a socket; review mode only opens the Anthropic request you explicitly asked for.

## Pro presets

If you want curated `.prpack.yml` configs for specific review styles — security, performance, architecture, test-coverage — plus a one-page workflow guide, see **[prpack Pro Pack](https://scottthurman89.itch.io/prpack)** (free or pay-what-you-want). The CLI is and stays free; the pack is optional.

## Contributing

See [CONTRIBUTING.md](./CONTRIBUTING.md). Good first issues are listed at the bottom — comment before you start so we don't duplicate work.

## License

MIT.