Flowery – Vocabulary builder powered by LLM and spaced repetition
Dear hackers: Whether English is your first or nth natural language, you may be familiar with this vexing experience: You encounter a flowery word in a book, podcast, or HN comment; you endeavor to memorize it to hone your speech and writing; you purge it from your synapses by the next day. Flowery (https://flowery.app) streamlines vocabulary building by: • Rendering a typographically pristine Oxford dictionary and thesaurus. • Conjuring up the stochastic parrot to eliminate the tedium of flashcard creation. • Scheduling the flashcards with a spaced repetition algorithm. About the…
In plain words
Flowery is a web-based vocabulary learning tool that helps users retain new words encountered in reading and listening. It uses an AI language model to automatically generate flashcards from words users save, then schedules review sessions using spaced repetition algorithms. The application includes access to Oxford dictionary and thesaurus definitions and is built for desktop and mobile browsers, with particular attention to iOS usability features.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Dear hackers: Whether English is your first or nth natural language, you may be familiar with this vexing experience: You encounter a flowery word in a book, podcast, or HN comment; you endeavor to memorize it to hone your speech and writing; you purge it from your synapses by the next day. Flowery (https://flowery.app) streamlines vocabulary building by: • Rendering a typographically pristine Oxford dictionary and thesaurus. • Conjuring up the stochastic parrot to eliminate the tedium of flashcard creation. • Scheduling the flashcards with a spaced repetition algorithm. About the tech stack: The server is built on Rust, Axum, and PostgreSQL. The client is built on Google’s Lit. We are betting the farm on the web—you won’t find Flowery on any app store. We have gone to great lengths to polish UX, especially on iOS where we rolled our own virtual keyboard, textboxes, and text selection. We strive to make Flowery an exemplar of the quasi-native web app. Non-obvious features to try: • “Add to Home Screen” on iOS. • “Add to Dock” on macOS Sonoma. • Install on Android and desktop Chrome. • Append an ellipsis to search by prefix. • Touch a flashcard’s blank for a hint. • Keyboard navigation inspired by the one true editor. Give it a whorl [sic] and share your thoughts! Florally yours, The Florist
Does the same job
all alternatives →
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 · 27d ago · cactuscompute.com
Launched alongside, June 2024
the whole month →
La Growth Machine▲1,216Create personalized, multi-channel conversations at scale
AI · 2024 · lagrowthmachine.com
PyjamaHR▲1,132Hiring on autopilot. The AI applicant tracking system (ATS).
Work · 2024 · pyjamahr.com