I'm going to try assigning each word in the database a positive/negative score and making sure that future word lists have a neutral average.

Earlier this year I moved to a new apartment, and scattered a box of poetry magnets all over my fridge. Whenever people came to visit, I noticed how they always loved making poems of their own, not to mention enjoying the poems others had already created. It became such a fun and entertaining tradition, (especially due to the range of creative messages that my friends chose) that I felt compelled to make a full stack project out of it.

While LLM agents have made the technical aspects of building a project like this easier, it took me a really long time to nail the algorithm for choosing daily word sets. I started with a huge collection (on the order of 100,000) of words, grouped by part of speech and sorted by the frequency of use in English. I tried randomly choosing a few words in the top 10, a few in the top 100, and so on, for each part of speech.

That straight up did not work. Trying to make poetry out of those wordsets felt terrible. It was very discouraging. I had to go back to the drawing board many times. My current solution came about when I found some databases of words, one sorted by their sensory value (from most to least sensory-evoking) and one where words are sorted on a spectrum of concreteness to abstractness.

Another key to picking fun and interesting word sets was ensuring there are a solid set of words that are included in every set no matter what. This "glue" set was handpicked by words that I found myself searching for over and over again when trying to write poems, but it is deliberately small to help people be creative in how they express ideas.

I used Deepseek v4.1 Flash and the Pi agent. My AGENTS.md emphasizes my status as a junior developer, specifically prompting the agent to never make architectural decisions on my behalf, to quiz me on the architecture/code involved before implementing changes I request, and to never write copy so I can make sure the site feels warm and genuine in my own words. I wanted to avoid letting the code get out of control for when I want to add features in the future.

One of the things I love about building these kinds of projects that LLMs enable is being able to add tiny features that most people will never see. For example, I added special effects that occur when a haiku is written.

I chose TanStack Start and React this time instead of SvelteKit. The experience was about the same. And kudos on poems are deliberately spammable. I like seeing number go up.

Friends have expressed enjoyment from using it so far, but I'm excited to hear feedback on y'all's experience and see if there's anything huge I'm missing. Thank you in advance!

Comments URL: https://news.ycombinator.com/item?id=50308899

Points: 3

# Comments: 2

Personally, I know Genesis/Exodus, Psalms, and the Gospels well. I can recognize Epistles on sight, but identifying the exact one is really just a guessing game. Most everything else I am not familiar with and will take me a while to guess.

I think that's why people have enjoyed it so far, because of the tradeoff of getting a verse you recognize (so you can guess the book quickly) or getting an unfamiliar verse (so you get to expand your familiarity with the Bible).

Perhaps I should make it clearer that correctly identifying the book on the first try is not the expectation. Maybe I will add a clarification that the goal is "as few guesses as possible" or maybe "as few guesses as you can".

It's quite a variable challenge. Sometimes it's easy, sometimes it's not. (Usually it's not.) I appreciate your feedback.

*Despite them both being in the same section. Oops.

I spent a decent amount of time trying to add the Deuterocanonical books. Ultimately I put it on hold, because I was worried that adding those books would make a challenging game even harder (at least for my initial audience of 20 family and friends). I also wondered if adding those books would put off any Protestant visitors... but I see their omission has caught your attention, that's Orthodox 1, Protestant 0. I'll find an elegant way to work them in.

And I never thought of adding an RSS feed! I'll add that to the todo!

I have absolutely no clue how I got the idea, other than the fact that I grew up in the Orthodox Church and all my other coding projects have been faith-related (a terrible mobile app (1) and slightly broken Byzantine chant website (2) ). I'm a relatively new developer and I've been hungry for a project to build that people will actually use and share around, so I hoped this would fit the bill.

Sure enough, friends and family have been making it part of their daily routine. When priests AND my nonreligious college friends started sending me their results every day, I knew I had something. It was really exciting.

------

When the idea popped into my head, I started working on it right away. I created the project at 1AM and had a MVP/SLC version done a few hours later. That was a few weeks ago.

I am using SvelteKit, no external APIs, and SQLite for the database. It's hosted on an Ubuntu machine in my living room. Coding agents like Roo/Kilo Code assisted heavily in the development, but after I had already decided on the overall architecture and how I wanted things to work together.

The game is free, has no signup, and I’m not running any ads. I’m looking for any and all feedback, and especially suggestions for how I can make the game more interesting, fun, and/or educational.

Thank you HN!

Comments URL: https://news.ycombinator.com/item?id=46541885

Points: 49

# Comments: 64

Every aspect of the games are narrated in real time so you know what's going on. I'm still in the prototype stage and I've seen some pretty hilarious interactions already.

Comments URL: https://news.ycombinator.com/item?id=44388013

Points: 5

# Comments: 0