Simedw
I build strange little systems with AI, software, and hardware.
simedw.com App StoreEducation / Language Learning
- Monthly visits
- 26.8K
- Up381.6%MoMOct 2026
- Public revenue
- Undisclosed
- No public revenue evidence yet
- Entry price
- Free
- No monthly subscription pricing
- Launched
- 17mo ago
- 2025-07-01 · Est.
Traffic
Marketing moves
Launches, search & content, referrals, promotionsLaunched on Show HN (3 pts)Launch
Harness Corp – An incremental game powered by a local LLM using WebGPU — I built a small browser incremental game where you start by answering tasks at your desk to save up to rent a GPU, and hire a real Qwen3-0…
Oct 28 · 24d agoLaunch page
At the time: 5.6K visits/moVisits: prior 1 mo +119%, next 1 mo +382%Launched on Show HN (506 pts · 106 comments)Launch
I trained a 125M model to autocomplete piano on-device — I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basic…
Aug 20 · 3mo agoLaunch page
Launched on Show HN (469 pts · 153 comments)Launch
I trained a 9M speech model to fix my Mandarin tones — Built this because tones are killing my spoken Mandarin and I can't reliably hear my own mistakes. It's a 9M Conformer-CTC model trained o…
Jan 31 · 10mo agoLaunch page
Launched on Show HN (84 pts · 29 comments)Launch
Learning a Language Using Only Words You Know — A proof-of-concept language learning app that uses LLMs to generate definitions of unknown words using only previously mastered vocabulary.
Dec 15, 2025 · 11mo agoLaunch page
Launched on Show HN (426 pts · 180 comments)Launch
Spegel, a Terminal Browser That Uses LLMs to Rewrite Webpages
Jul 1, 2025 · 17mo agoLaunch page
Third-party reviews & case dossiers
Acquisition breakdowns, engineer reviews & open-source metrics- Post excerpt:
- Built this because tones are killing my spoken Mandarin and I can't reliably hear my own mistakes. It's a 9M Conformer-CTC model trained on ~300h (AISHELL + Primewords), quantized to INT8 (11 MB), runs 100% in-browser via ONNX Runtime Web. Grades per-syllable pronunciation + tones with Viterbi forced alignment. Try it here: https://simedw.com/projects/ear/
- Post excerpt:
- 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
- Post excerpt:
- I built a small browser incremental game where you start by answering tasks at your desk to save up to rent a GPU, and hire a real Qwen3-0.6B model running locally in your browser over WebGPU (~358 MB download). Throughout the game you buy upgrades to your model's harness, things like JSON structured output or date tools. This actually changes how the model
Traffic sources
Traffic breakdown
No traffic channel or country breakdown data for this website yet.
Search
Domain authority —Domain registered 2013-11-18
No search keyword data for this website yet.
Traffic data: Vaneform
Pricing
Pricing page not identified yet, or no public pricing listed.
Website snapshots
Key pages
Desktop & mobile archiveWebsite snapshots pending capture.
Design
Minimal Monochrome (Light canvas, airy density) featuring editorial serif headline layout and pure typography & geometry visuals.
First-screen preview · click to zoom
First-screen pitch & conversion flow
“Harness Corp: a game about making a 0.6B model useful”
Editorial Serif Headline hero structure paired with direct input / instant try CTA and no explicit trust bar.
Conversion path: Editorial Serif Headline + Pure Typography & Geometry → Direct Input / Instant Try
- Category Positioning Anchor
Palette · click to copy
- Typography
- 8.0
- Color & Contrast
- 7.0
- Layout & Spacing
- 8.0
- Craft & Polish
- 7.0
- Distinctiveness
- 7.0
Structure
- Fonts
- Inter / 等宽字体
- Hero layout
- Editorial Serif Headline
- Primary visual
- Pure Typography & Geometry
- Conversion CTA
- Direct Input / Instant Try
- Social proof
- No Explicit Trust Bar
- Navigation
- Full-Width Top Bar
- Theme & density
- Light · Airy
- Corners & depth
- Medium Radius · Hairline borders
Preview full AI design brief (includes :root CSS variables & layout rules)Style tokens only; never copy brand names, logos, copy, or images
# Design Brief: Minimal Monochrome (with Dark Developer)
Monochrome palette with a single accent color, hairline dividers, and generous whitespace.
## Design Tokens
```css
:root {
--background: #ffffff;
--surface: #f3f3f3;
--foreground: #111827;
--muted-foreground: #374151;
--accent: #4f46e5;
--radius: 8px;
--font-heading: "Inter", ui-sans-serif, system-ui, sans-serif;
--font-body: "Inter", ui-sans-serif, system-ui, sans-serif;
--font-mono: "等宽字体", ui-sans-serif, system-ui, sans-serif;
}
```
Color area ratio: Background #FFFFFF (~74%) · Surface #F3F3F3 (~15%) · Text #111827 (~6%) · Muted Text #374151 (~3%) · Accent #4F46E5 (~2%). Background and surface dominate the canvas; reserve the accent color for primary buttons and active states.
## Layout & Conversion Structure
- Hero layout: Editorial Serif Headline
- Navigation: Full-Width Top Bar
- Theme & density: Light · Airy
- Border radius & elevation: Medium Radius; no drop shadows—separate layers with hairline borders and whitespace
- Primary visual medium: Pure Typography & Geometry
- Conversion CTA: Direct Input / Instant Try
- Headline hook: Category Positioning Anchor
- Spatial layout notes: Editorial Serif Headline hero structure paired with direct input / instant try CTA and no explicit trust bar.
- Visual summary: Minimal Monochrome (Light canvas, airy density) featuring editorial serif headline layout and pure typography & geometry visuals.
## Avoid
- Multi-stop neon gradients
- Heavy drop shadows
- More than one competing accent color
Implement the UI following the design tokens and layout specifications above: use only these color variables, and reserve the accent color strictly for primary actions and active states. Adopt only this visual style—never copy any reference product’s brand name, logo, copy, or imagery.
Questions & evidence
- How much website traffic does Simedw get?
- Vaneform estimates 26.8K website visits in 2026-10. Visits can include repeat visits; this estimate measures web traffic separately from paying customers or revenue.Source
- What is Simedw and what platforms does it support?
- Simedw is catalogued under Language Learning: I build strange little systems with AI, software, and hardware. Supported platforms: Mobile App.
Related products in this category
These products share a catalog category. Compare customer tasks, features and deployment requirements before treating them as alternatives.
| Product | Entry price | Visits | Revenue |
|---|---|---|---|
| DuolingoGiantThe most fun way to learn languages, chess, and more! | — | 57M | Undisclosed |
| PreplyGiantLearn with a tutor who turns lessons into real progress. | — | 30.4M | Undisclosed |
| InoriginalMatureРекомендуем | — | 5M | Undisclosed |
| LexilogosMatureDictionnaires, Cartes, Livres en ligne - Langues & pays du monde | — | 4.4M | Undisclosed |
| VocabularyMatureLook up a word, learn it forever. | — | 3.1M | Undisclosed |
| WaniKaniMature2,000 kanji. 6,000 vocabulary words. In just over a year. | — | 2.8M | Undisclosed |