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

量子位
博客园_首页
Google DeepMind News
Google DeepMind News
博客园 - Franky
The GitHub Blog
The GitHub Blog
GbyAI
GbyAI
有赞技术团队
有赞技术团队
Microsoft Azure Blog
Microsoft Azure Blog
G
Google Developers Blog
Recent Announcements
Recent Announcements
A
About on SuperTechFans
博客园 - 【当耐特】
博客园 - 三生石上(FineUI控件)
酷 壳 – CoolShell
酷 壳 – CoolShell
美团技术团队
罗磊的独立博客
IT之家
IT之家
博客园 - 聂微东
Stack Overflow Blog
Stack Overflow Blog
Jina AI
Jina AI
腾讯CDC
P
Proofpoint News Feed
Hugging Face - Blog
Hugging Face - Blog
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

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 - 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 - piqoni/piqo-extension: A good interface is invis...
lexoj · 2026-05-18 · via Hacker News - Newest: "LLM"

A chat-less way to collaborate with your favorite LLM models (remote or local), directly from your files and from any editor. The output is stored automatically into your files.

It is a simple file-watcher extension for pi triggered on-save, which monitors directories for @piqo markers and uses the LLM to generate content inline.

Might be useful for keeping notes, writing tasks, researching topics, etc.

Random Example: If you write the following (highlighted line) and save the file: Image

You will get something like (using gpt-5.4-mini):

Image

How It Works

  1. You start pi with the piqo extension and specify directories to watch
  2. Piqo recursively watches those directories for file changes
  3. When a file contains one or more @piqo <instruction> markers, it reads the file, gathers context around all markers, and sends them to pi's LLM in one request
  4. The LLM fulfills each prompt and removes the human prompt line/tag from the file

Usage

If you have Pi installed, you are one command away from using it:

# Load it directly from github
pi -e https://github.com/piqoni/piqo-extension --dir=/path/to/your/project

# Or if you want to reference it locally, git clone the repo and reference it directly
pi -e ./piqo-extension --dir /path/to/your/project

# Watch multiple directories
pi -e ./piqo-extension --dir /path/to/dir1,/path/to/dir2

# Headless mode (no TUI)
pi -e ./piqo-extension --dir /path/to/project -p "Start piqo watcher"

Marker Format

In any text file within the watched directories, add:

@piqo <your instruction here>

The LLM will process it and replace/remove the prompt so the file becomes:

... generated content ...

Examples

In a Python file:

# @piqo add a function to parse CSV files and return a list of dicts

# Becomes generated code with the @piqo prompt removed

In a Markdown file:

@piqo write a summary of REST API best practices

Becomes generated content with the @piqo prompt removed

In a config file:

# @piqo add sensible default nginx config for a Node.js app

# Becomes generated config with the @piqo prompt removed

Behavior Details

  • Debounce: File changes are debounced at 500ms per file to avoid duplicate processing
  • Initial scan: On startup, piqo scans all watched directories for existing markers
  • Ignored paths: Hidden files/dirs, node_modules, .git are automatically skipped
  • Text files only: Only processes common text file extensions (.ts, .js, .py, .md, .txt, etc.)

Installation

Place this extension in ~/.pi/agent/extensions/piqo/ for global access, or reference it directly:

pi -e /path/to/piqo-extension