Show HN: How random are you?
- ID
- 35935
- Status
- summarized
- Published
- 14 Oct 2026, 12:57 AM
- Fetched
- 16 Oct 2026, 1:37 AM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- https://lab.specr.net/rigged-draw/
- Source URL
- https://hnrss.org/best
Summary
- Score
- 6.0
- Created
- 16 Oct 2026, 1:38 AM
- Tags
- Audience
- developersvibe_codersai_ml_learners
What happened
Show HN project "How random are you?" (lab.specr.net/rigged-draw, credited on the page to Shaun Pedicini) turns a browser page into a live guessing game: you say digits 1-9 out loud as randomly as you can, and the house seals its guess in an envelope before each number, then opens it. It runs speech recognition fully in-browser via a ~31 MB one-time speech pack (audio never leaves the page), skips the first 10 numbers as warm-up, and scores your hit rate against 206 people from a psychology study while seeding its model from 418 people who each picked 200 numbers from 1 to 9. Ten small predictors run at once and it trusts whichever has been right lately, with the "numbers you haven't said in a while" predictor doing most of the work. The thread drew 213 points and 119 comments.
Why it matters
It is a concrete reference for shipping an ML feature with zero server inference: speech recognition plus a ten-predictor online ensemble, all client-side, with the only cost being a ~31 MB one-time model download — worth weighing if your users are on metered mobile data, since that download is a real friction point you can't hide behind a spinner. The design detail worth copying is the prior: instead of cold-starting, it bootstraps from 418 people x 200 picks and then adapts per user, and it tracks per-predictor recent accuracy rather than averaging. Nothing here requires you to change a system today; treat it as a demo with a readable architecture, not an announcement.
Discussion angle
The site admits typing "makes for a weaker test" and that peeking stops the house's record counting as evidence — so how much of the 206-person comparison is a real randomness measurement versus a well-framed game? Ask the room whether shipping a 31 MB model download for a client-side feature is acceptable for Malaysian mobile users, or whether you'd degrade to a smaller model / typed fallback.