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

大猫的无限游戏
大猫的无限游戏
云风的 BLOG
云风的 BLOG
小众软件
小众软件
V
V2EX
博客园 - Franky
博客园 - 司徒正美
Apple Machine Learning Research
Apple Machine Learning Research
量子位
博客园 - 【当耐特】
雷峰网
雷峰网
WordPress大学
WordPress大学
Jina AI
Jina AI
Google DeepMind News
Google DeepMind News
N
Netflix TechBlog - Medium
爱范儿
爱范儿
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
阮一峰的网络日志
阮一峰的网络日志
IT之家
IT之家
Blog — PlanetScale
Blog — PlanetScale
Hugging Face - Blog
Hugging Face - Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
V
Visual Studio Blog
Microsoft Security Blog
Microsoft Security Blog

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店
Appareo — Write Like a Human
ShaunakInamd · 2026-06-22 · via Hacker News: Show HN

You Have Something
Worth Saying.

Most AI tools put words in your mouth. Appareo pulls them out. It interviews you, finds the clarity in your thinking, and drafts in your voice.

AI Slop

In today's fast-paced world...

Let's dive in...

It's worth noting that...

As we navigate the complexities...

In conclusion, it is clear...

Without further ado...

Your Voice

I thought I knew what I believed until I had to write it down.

The version of events I told myself and the one that happened are different.

There is a thing I have been meaning to say for about three years.

I watched my father do this for forty years and never asked him why.

It was a small moment. I keep returning to it.

I was completely wrong. Here is what actually changed my mind.

You have been staring at a blank page. The ideas are there, good ones, but somewhere between your brain and the screen they dissolve into mush.

That is not writer's block. That is a clarity problem.

So you tried AI. It handed you 800 words that could have been written by anyone. Same opening lines. Same transitions. Same hollow conclusions.

You published someone else's mediocrity.

Writing that matters never came from prompts. It never will.

It finds the thread and then it weaves your words, not its own.

Appareo is that conversation. It interviews you the way a good editor would.

The piece you could never start writing is already in you.

You will write faster. But that is not the point.

Clear thinking, finally on the page. Your voice, not a simulation of one.

How It Works

Three steps. No prompt engineering.

1

We Have a Conversation

We ask you the kind of questions a curious friend would ask over coffee. About your topic, your opinions, the stories only you can tell. Your answers are the raw material.

6-8 thoughtful questions. Not a form.

2

We Study How You Write

Paste something you've written before — a blog post, an email, a rant in your notes app. We learn your rhythms, word choices, and quirks. Not to copy you. To channel you.

Your fingerprint, not a template.

3

We Draft in Your Voice

Your ideas + your voice + narrative structure = a draft that reads like you wrote it on a clear-headed morning. Edit it, refine it, make it yours. Then publish.

To Substack, Medium, or anywhere.

Your Next Piece Starts
With a Conversation.

Stop staring at the blank page. Start talking.

Start Writing

No credit card required.