2025년 9월 5일의 Show HN

Hey HN! I'm Zach from Adam (https://adam.new/). We’re building an AI co-pilot for mechanical CAD software.

As part of our broader research, we built a browser-based Text-to-CAD app (https://news.ycombinator.com/item?id=44182206) and are now open sourcing it. This is a React SPA with a Supabase backend.

What it does:

* Generates parametric 3D models from natural language descriptions, with support for both text prompts and image references

* Outputs OpenSCAD code with automatically extracted parameters that surface as interactive sliders for instant dimension tweaking

* Exports as .STL or .SCAD

Under the hood:

* Separate agents for conversation and code generation; simple parameter tweaks bypass AI entirely using deterministic regex-based updates

* Runs fully in-browser by compiling OpenSCAD to WebAssembly and integrating Three.js with React Three Fiber for 3D rendering

* Supports BOSL, BOSL2, MCAD libraries and custom font support (Geist) for text in models

We’ve seen many developers trying to replicate this kind of functionality, so we’re releasing this to give the community a solid foundation to build on.

Future improvements:

* Expand geometry support - Move beyond CSG primitives to support curved surfaces, fillets, lofts, and constraint-driven modeling through CadQuery/Build123D

* Better spatial context - UI for face/edge selection and viewport image integration to give LLMs spatial understanding

* Enhanced capabilities - RAG on documentation and integration with more OpenSCAD libraries for features like proper threading

You can clone the repo and run it locally! Contributions are welcome, and we’ll keep merging PRs as they come in.

P.S. We’re also working on a tool that allows mechanical engineers to use text, images, or mechanical drawings to generate feature-rich CAD models in their favorite platforms. If working on AI CAD sounds interesting to you, check out our careers page at https://adam.new/careers.

This is the first half of my book, “Swimming in Tech Debt”. It is available at a pre-launch sale price of $0.99 (https://loufranco.com/tech-debt-book).

I have been working on it since January 2024. It is based on some posts in my blog, but expands on my ideas quite a bit.

In September 2024, excerpts appeared in Gergely Orosz’s Pragmatic Engineer newsletter, which helped me get a lot of feedback that expanded the book from my initial idea. This half is about what I expected to do before that —- the rest of the book goes into team and CTO practices.

Hello! I am coparenting... and hated having to ask my baby daddy to pay for my sons clothing, school supplies groceries etc bc I had to add everything up. So I fixed it! I

- upload reciepts/bankstatements (no uploads saved)

- in description say the kinds of things you want to add up, even some math (like split)

- tally adds it up

it splits the costs if you add in the word split in the description. perfect for people who need to split costs, like gas, daycare, etc. would love any feedback. totally free! one day i will add a paywall, is daycare is EXPENSIVE.

Backstory: Few years back, I used a shared spreadsheet (GSheets) to organize my property hunt, and found it quite frustrating to keep on top of things just on the productivity side alone.

Felt that there should be a better way to do this, and that's when I started creating a webapp, with features that can make this journey feel less stressful.

This is a solo dev project. Have a look at the demo, and let me know your thoughts!

Cheers

And yes, I know, literally no AI uses llms.txt right now.

But hear me out: if you want it just in case, or if you would like to add your sites to some llms.txt directories, you can use this endpoint. That way, you do not need to keep updating your own llms.txt, especially as I improve the API.

Here is how it works:

Enter any domain:

https://get.llms.page/{example.com}/llms.txt

The API will parse your homepage (if allowed in robots). Using internal links, descriptions, and other metadata, it will generate an Markdown llms.txt file.

It does not rely on AI, because I want it to be fast and free. The API is open, free, runs on a CDN, and is powered by Cloudflare Workers for speed.

I plan to open source the no-AI llms.txt generator later, since there is still a lot to improve.

If you want to try it out or see some usage examples, visit:

https://llms.page

Let me know what you think!

Scrape the most recent congressional stock trading.

Most people now get their news from social feeds — but those feeds reward popularity, not accuracy. Misinformation spreads fast, and even well-intentioned users often can’t tell what’s reliable.

I’ve been working on a different approach: a social/news platform where every post carries a credibility score. Instead of likes or shares, users assess posts by linking to supporting or refuting sources. Credibility then updates across posts, users, and domains in real time.

A few things that might interest HN:

- Anonymous/pseudonymous accounts (no personal brands driving popularity).

- Credibility > virality: feeds are sorted by time & trustworthiness, not engagement.

- URL and domain-level scoring: credibility of sources builds over time.

- Four feeds: Front Page, Bullpen, Cred Desk, and Subscriptions (you can filter by credibility percentile).

It’s in public beta here: https://noblenews.io

Curious what HN thinks:

- How might this system be gamed or abused? - What are your thoughts on pseudonymous usernames? - What would make it more useful for people who actually want reliable news?

Domain-specific fine-tunable vector search leveraging signals energy

When I tried to set up my first lead magnet funnel, I hit a wall. What was supposed to be a simple "give away a free guide in exchange for emails”"turned into a mess of picking an email provider, wiring forms, building automations, and making sure everything was GDPR-compliant.

I realized this is the same pain many creators face: too much setup just to share a freebie.

So I built freebie.email...the domain is cool, eh

How it works: - Upload your freebie (PDF, checklist, template, etc.) - Get a unique link to share anywhere (bio, website, social) - Collect emails automatically - Subscribers receive the file instantly—no integrations, no configs

That’s it. Minimal, distraction-free, and built for creators who just want to ship.

I’d love your feedback—the good, the bad, or the weird. What’s missing? What confused you? What features would make it indispensable?

Hey HN, this is our weird little soccer + chess daily puzzle game. The puzzle generation (and the rest of the backend) is written in C#/Razor, and the frontend is a mix of Pixi.js and regular web stuff.

The game has kind of a strange structure, where each puzzle represents a match that took place in an imaginary soccer league... so you're not determining the outcome of the soccer match, but you are recreating what happened.

Note: If you solve each goal perfectly (using the minimum number of kicks), then it unlocks a harder bonus goal. You can also go back and play past puzzles from earlier in the season if you want to try some more puzzles.

Hi HN I’m Tina. One frustration I keep running into with LLMs is hallucinations: answers that sound confident but are fabricated. Fake citations, wrong numbers, even entire “system reports.” So I’ve been building CompareGPT, which tries to make AI outputs more trustworthy by: Putting multiple LLMs side by side for the same query Making it easy to see consistency (or lack of it) Helping catch hallucinations before they waste time or cause harm link here：https://comparegpt.io/home. We’ve opened a waitlist and would love feedback, especially from folks working with LLMs in research, finance, or law. Thanks!

nano banana is hot right now, but how to use it create image as you wish is a problem. so it is what nanobananaprompt.app come help. you can find over 50+ professional prompts across categories (3D rendering, photorealistic, illustrations, etc.), can get this prompt and try it now.

ProcASM is general purpose, visual programming language that I've developed. A few months ago I made a post about ProcASM v1.0 here <https://news.ycombinator.com/item?id=43892442> and got some feed about the UI.

So, I spent that last few months trying to improve the UI. Before, I used a GUI library, that I developed specifically for this app using SDL3, for ProcASM. I used Emscripten to port it to run in web browsers for those who wanted to try the app. Now, the front-end is written in HTML, CSS, and JavaScript to execute in a web browser. The back-end is a server that stores user's projects and handles user's requests. There is also a tutorial with text and video that will walk you through the usage of the app. My hopes are that the UI will be more approachable for those who want to try out the app.

The plan going forward is to develop new software using ProcASM and blog about the details and the advantages of using ProcASM.

I have created a tool that will allow users to obtain designs and ideas for planning a wedding.

The goal is to save time for those in charge of organizing the event by allowing them to create images with AI based on parameters that the user can define.

The tool currently has different features: - Wedding dress designer: A bride can define what type of dress she likes best, the design of the sleeves or train she wants, and her body type. In a matter of seconds, she will have some ideas. - Banquet designer - Ceremony designer - Wedding invitation card designer

It also has an image editor that allows you to upload your photo and request changes.

Who benefits from this tool? - Couples: They save time and allow you to see the expected result without surprises. - Wedding planners: They look for alternatives according to the client's criteria. - Venue owners: They can decorate professionally, saving a lot of money and gaining unlimited inspiration. - Content creators: They can create endless content on social media thanks to the combination of images and designs.

If you like the idea, I invite you to try it with a 30% discount using the code WELCOME30.

I look forward to your feedback, thank you very much in advance.

Best regards!