70 Days → 800 GitHub Stars (Cold Start) – My Secret Was a Problem Map
Hi HN, I want to share a story that might resonate with anyone who has tried to launch an open-source project from zero visibility, zero budget, zero network. Seventy days ago I created a repo called WFGY. I had no prior followers, no launch partners, no ads. Today, it’s at 800 stars and counting. Pure cold start. The “secret”? Not marketing. Not tricks. It was building a Problem Map. --- #### What is a Problem Map? Instead of claiming my system “improves reasoning” or “solves RAG bugs,” I wrote down 16 concrete failure modes engineers hit every day: * Embedding drift (semantic ≠ vector…
What it does
In the maker’s words, at launch
Hi HN, I want to share a story that might resonate with anyone who has tried to launch an open-source project from zero visibility, zero budget, zero network. Seventy days ago I created a repo called WFGY. I had no prior followers, no launch partners, no ads. Today, it’s at 800 stars and counting. Pure cold start. The “secret”? Not marketing. Not tricks. It was building a Problem Map. --- #### What is a Problem Map? Instead of claiming my system “improves reasoning” or “solves RAG bugs,” I wrote down 16 concrete failure modes engineers hit every day: * Embedding drift (semantic ≠ vector closeness) * Chunking collapse (half-sentence vs full chapter granularity mismatch) * Versioning hallucinations (index v1 + v2 = ghost hybrid doc) * Pre-deployment ingestion collapse * Prompt injection bypasses * … and 10 more, all documented. For each one I built a text-only “semantic firewall” module that fixes the issue without changing infra. Developers could see their exact bug listed, mapped, and patched. This gave the repo two things: 1. Immediate empathy — engineers recognized their pain points word-for-word. 2. Immediate usability — they could paste my TXT file, keep infra untouched, and the model stabilized. --- #### Why it mattered * It wasn’t a claim, it was a diagnostic mirror. * People didn’t need to “believe” me — they could try the TXT in 60 seconds and watch bugs stop replicating. * Instead of selling “AI magic,” I showed a surgical checklist. This is why strangers starred the repo. It wasn’t hype; it was problem → fix → proof. --- #### What’s next I’m now scaling this into something bigger: * The Problem Map will evolve into a Global Semantic Surgery Room — think of it like an AI hospital’s operating theater. * Engineers bring in failure logs (RAG, OCR, planning drift). * The system triages, diagnoses, and applies the right semantic patch in real time. * Integrations are underway for n8n, Make, GoHighLevel and more — all unified under the same open Problem Map. Launch target: September 1. ### Closing I don’t see this as “my repo got stars.” I see it as proof that open source thrives when you solve pain with surgical precision. If you’ve ever tried to cold start, my suggestion: don’t sell a dream, map a nightmare. Engineers don’t trust hype — they trust a checklist that fixes the crash. Coming next: the Semantic Surgery Room and Global Fix Map (n8n, GHL, Make and more). Launching by Sep 1.
Does the same job
all alternatives →
- ISI started a repo for sharing algorithm implementations2013 · github.com · ▲52
Everything that would be here is in the README. I hope this gets big, it has tons of potential.
- MWmy weekend project, understanding the Silk Road anonymous marketplace2011 · burntbrunch.github.com · ▲40
This was more of a sandbox to play with Raphael and Flot than anything else but I think there are some interesting statistics in there. It'd be awesome to do this over time but I really don't have the spare time required.
- SLsoft-launching one of my pet projects2011 · ▲27
So a while ago I was thinking it would be neat to build a site that had the most absolute utility. The idea I came up with was a site to store those little protips that are super useful, if you know them ahead of time. I hired a guy to work on it with me, and ClueDB was born: http://cluedb.com/ Please give it a whirl (it uses Twitter auth as login but doesn't tweet anything) and tell me what you think! (Various trivia: My first try at a project coded by someone else and "product managed" by me. Runs on Flask + MongoDB. Also, this is totally unrelated to my startup.)
- IMI'm a non-hacker "idea guy" and my weekend project took 1,670 + days2012 · ▲21
I am a non-hacker "idea guy" with zero discernible talent. Like most, the story starts with me doing things the hard way. I dreamt of a tool that would save me countless hours. Like most of my ideas, it was supposed to die in a couple of hours, but this one had some legs.... "If I needed this, surely others did too" kept looping in my head. Could I get this built? Could I build it myself? Nah...too lazy to learn how, but before I did anything, I had to promise myself one thing: No more ideas! If ideas were sit-ups, I would have a six pack instead of this tire. It was a constant mental…
- HMHoodmaps Meets 4chan2024 · mapchan.com · ▲8
I made this as a pair programming exercise with o1-preview. o1 did most of the heavy lifting, through high level prompts, but eventually I needed to diverge from it to get to completion. My initial prompt was: --- I'm making a web app: It's like 4chan, but each thread starts with a gps coordinate. People can only post text and images. I want to build it with flask and sqlalchemy. I want just the backend and data model that supports these threads, anonymous users, and users that can register a permanent username. Write as much of it as you can for me. --- This produced a fully scaffolded…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2025
the whole month →
- IS
I built the world's most impractical 1000-pixel display and anyone in the world can draw on it. It draws a single pixel at a time and takes 30-60 minutes to complete a single image. Anyone can participate in the project by voting for the next image to be drawn, and submitting images. https://kilopx.com/
Work · 2025 · benholmen.com
- KT
Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…
Dev tools · 2025 · github.com
- IW
I was wondering how I can arrange objects along a spherical helix path, and read some articles on it. I ended up learning about parametric equations again, and make this visualization to document what I learned: https://visualrambling.space/moving-objects-in-3d/ feel free to visit and let me know what you think!
Life & fun · 2025 · visualrambling.space
- TC
For HTML Day 2025 [1], I made a web service that displays the current sky at your approximate location as a CSS gradient. Colours are simulated on-demand using atmospheric absorption and scattering coefficients. Updates every minute, without the use of client-side JavaScript. Source code and additional information is available on GitHub: https://github.com/dnlzro/horizon [1] https://html.energy/html-day/2025/index.html
Dev tools · 2025 · sky.dlazaro.ca