So I built AIRiskCalc. It's a collection of free health risk assessment tools with AI interpretation.

Currently live with five calculators:

ASCVD Risk (10-year cardiovascular risk based on ACC/AHA 2013 Pooled Cohort Equations) Type 2 Diabetes Risk (ADA assessment model) Cardiovascular Risk (multi-factor evaluation) CVD Risk (cerebrovascular focus) Miscarriage Risk (early pregnancy assessment) Implementation: Next.js 15, Cloudflare Pages. AI layer uses Vercel AI SDK with Claude.

One detail I paid attention to: the ASCVD formula involves logarithmic transformations and coefficient matrices from the original 2013 paper. I transcribed the equations into TypeScript and verified against sample data in the paper's appendix.

Each calculator displays the reference source in code comments. Results include AI-generated explanations of what the numbers mean. No personal data is collected.

The question I'm thinking about: where's the line between helpful AI interpretation and overstepping into medical advice? I want the tool to be useful without replacing professional judgment.

Feedback welcome on this balance.

Comments URL: https://news.ycombinator.com/item?id=47335719

Points: 2

# Comments: 2

But recently, I experimented with "vibe coding"—where I focus on the logic and flow, and let AI handle the implementation details. The result is AIMovieQuotes (https://www.aimoviequotes.com).

It is a simple but useful engine: you search for iconic lines from movies, TV, and songs by mood, theme, or keyword.

The process was a revelation. In the past, I would have abandoned this project when the CSS broke or the database queries got complex. This time, I acted as the architect. I described the outcome, and the AI paved the road.

For the first time, I felt the pure joy of creation rather than the frustration of debugging.

I am sharing this not just to show off the tool, but to share a realization: The gap between "having an idea" and "shipping a product" is vanishing. Even for a "weak" coder like me, building a complete product is now possible.

I hope you find the quotes you need, but more importantly, I hope this encourages other juniors to stop worrying about syntax and start shipping.

Comments URL: https://news.ycombinator.com/item?id=46750116

Points: 1

# Comments: 0

It’s a tool to find meaningful quotes from movies by searching with a movie title and a theme (like “love,” “betrayal,” or “courage”).

The problem it solves: I often wanted to find a specific quote from a movie that captured a certain feeling, but couldn’t remember the exact words. Traditional keyword searches on existing quote databases are too literal. If you search for “love quote from Inception,” you might get nothing, even if the movie has lines deeply related to the concept of love.

How it works (the technical side): Instead of relying on keyword matching, the tool uses an embedding model to convert movie dialogues and the user’s query into high-dimensional vectors. It then performs a semantic similarity search to find the most conceptually relevant lines, even if they don’t contain the exact keyword. The front end is a simple static site built with Next.js, and the search is handled by a serverless function calling a vector database.

Why I built it: This was a weekend project to experiment with applying semantic search to a concrete, everyday problem outside of the typical enterprise or coding contexts (like documentation search). It demonstrates how AI can understand the meaning behind a request rather than just matching words.

I’d be interested in your feedback, especially on:

The accuracy of the quote matches. Ideas for other non-traditional datasets where semantic search could be useful. The overall user experience. Try it out here: https://www.aimoviequotes.com

Comments URL: https://news.ycombinator.com/item?id=45679060

Points: 1

# Comments: 0

I'm excited to share a project I've been passionately working on in my spare time: AI Movie Finder (https://www.aimoviefinder.com).

The idea was born out of a simple, yet frequent, frustration: having a movie on the tip of my tongue but being unable to recall the title. All I could remember were fragments – a specific scene, a snippet of dialogue, the general plot, or even just the mood it evoked. Traditional search engines often fell short with these kinds of abstract queries.

So, I decided to build a solution. AI Movie Finder uses a natural language processing model to understand these descriptive and sometimes vague queries. You can type in things like:

"that movie where a guy keeps reliving the same day"

"a sci-fi film with a blue alien opera singer"

"a feel-good movie about a band in the 80s"

The goal is to make movie discovery more intuitive and human-like. Instead of just searching by actors or exact titles, you can search by memory and feeling.

The backend is built with Python and utilizes a fine-tuned sentence transformer model to create vector embeddings for a large movie database. The frontend is a clean and simple interface built with vanilla JavaScript to keep it fast and accessible.

This is still very much a work in progress, and the database is continuously growing. I'm actively working on improving the model's accuracy and expanding the search capabilities.

I would love to get your feedback. Please give it a try and let me know what you think. I'm particularly interested in:

How well does it work for your queries?

Are there any features you think would be a great addition?

Any suggestions on how to improve the model or the user experience?

Thanks for checking it out! I'll be here to answer any questions.

Comments URL: https://news.ycombinator.com/item?id=44529525

Points: 10

# Comments: 3