The app uses DISTAR phonics, which is a method from the 60s by Siegfried Engelmann. The core idea is simple: teach sounds before letter names, then blend sounds into words, then words into sentences. There's a specific sequence that builds on itself.

On top of that I added spaced repetition, same algorithm as Anki. Cards come back at increasing intervals depending on how well the kid does. This keeps sessions short, maybe 5-10 minutes, and the retention is noticeably better than just drilling the same set of cards every day.

Each card has an AI-generated illustration and spoken audio. All 721 cards are pre-generated and bundled with the app. Nothing calls an API. The whole thing works offline.

What's in it: 721 cards (letters, digraphs, words, sentences), speech recognition for pronunciation practice, no account, no data collection, no ads. Source is on GitHub.

She's been using it for a bit more than 3 months now, roughly 10 minutes a day. She can now recognize phonetic patterns in words and read simple books in English.

No monetization, no data tracking whatsoever. Also available for free on the App Store (if you don't want to deal with the hassle of compiling the app from source): https://apps.apple.com/us/app/early-reader-preschool/id67571...

Comments URL: https://news.ycombinator.com/item?id=47762556

Points: 5

# Comments: 2

But they were not trained on government-sanctioned homegrown EU data.

Wasn’t he literally scanning eye balls a couple years ago?

Interesting idea, but how do you address car safety concerns? Studies consistently show that cognitive distraction, even with voice interfaces, can significantly increase crash risk. Wouldn’t managing emails and calendars while driving still fall into that category?

The tool listings are not necessarily a secret, so not sure how this is "exposed". We have a public MCP, anyone can read our tool listings, but to actually use the tools you need to authenticate.

But what's driving a car? A generalist human brain that has been trained for ~30 hours to drive a car.

> the crosshair briefly changes to confirm the hit, damage numbers pop up above the enemy, sound effects, enemy death animations, a progress bar filling up, a new skill unlocked, random reward and more...

I wonder if we can gamify todo apps in the same way, most are too boring and too corporate. It should implement all gaming bells and whistles for ensuring you complete your tasks.

I like this hedging strategy, can probably also apply this to the risk of AI taking over our jobs (licensed professions won’t be going away any time soon).

Don’t ask me how I know :) It is one of the few accountability sinks that doesn’t affect me negatively.

1) Someone actually thought this was a good idea

2) Someone actually built it

3) YC actually funded it