WhittleOS
Decide which startup idea is worth building
What it does
Most idea validators are feel-good machines: paste an idea, get a "promising" score, build for months on a vibe. WhittleOS is the opposite — deliberately kill-biased. It sources real candidates itself, links the problems it cites to the page each was read on or says when it's our own estimate, computes the score in code (not the model's own number), and returns nothing when a market's weak. Build / test-first / drop, with the reasons. No calls. Real, unedited run: whittleos.com/sample-discovery
Kill weak startup ideas before they waste your months. A startup decision engine for solo founders.
A decision tool for one-person businesses. It searches, it drops what has no real problem behind it, and it is built to say no. Start wherever you actually are. Get a straight answer: build it, test it, or drop it — with the reasons attached. Free with the 2 credits you get on signup — no card required. We'll go and find you some — from real market data, not a model's memory. Step 1 is free. The search itself is from 2 credits , which the signup credits don't cover — see a real run first . A verdict, a score for one person, the reasons behind it, and one thing to do next — plus the point where you should walk away. Door one returns this for the idea you bring. Door two returns up to 5 of…from whittleos.com
Does the same job
all alternatives →
- ASA site to help you validate ideas in bulk2020 · ▲93
Hi HN! I made a really quick web app to help people validate their ideas. The app is a simple landing page builder, but every page includes a really simple Yes/No "Are You Interested?" poll. Every vote is recorded and tracked, and if they click yes they are brought to a page where they can submit an email. This makes validating ideas super easy because you can post your link to different communities and get statistically significant results as well as build an email list. Given an hour, you could easily create 50 different landing pages and be able to validate your ideas in bulk. The…
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 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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