LoveRace

What the company appears to be: LoveRace is a self-reported web application that uses real-world demographic and social data to model the probability of finding a compatible romantic partner, based on user-defined preferences. It is built as a dependency-free, publicly accessible tool using HTML, CSS, and JavaScript, hosted via GitHub Pages.

What changed: The author states that this project was an evolution of an idea originally conceived years ago in Excel, which they were unable to fully realize due to complexity and lack of tools. With the help of Codex (a generative AI), they transformed it into a functional web application with statistical modeling, data visualization, and iterative design.

Single most important open question: Is there any evidence that users are engaging with or adopting this tool beyond its initial development and public release?

The description states that LoveRace is a dependency-free web application built with semantic HTML, custom CSS, and vanilla JavaScript. It is published free through GitHub Pages and has no framework, build process, database, or paid hosting requirements.

It uses the World Bank API for current world population, country population, and GDP-per-capita data, with fallback values when the API is unavailable.

The application models partner pool size using a formula:

$$N_{pool} = N_0 \prod_{i=1}^{k} f_i$$

It calculates probability of meeting someone based on:

• Geographic relevance ($r_g$)
• Mutual connection assumption ($r_c$)
• Number of people met per week ($m$)

The tool estimates how long it would take to reach 20%, 50%, and 80% cumulative chance of finding a compatible partner.

It presents results in an editorial data experience, not a dating app interface, with strong typography, restrained color palette, and small evidence labels.

Not evidenced: No revenue model, no customer base, no usage metrics, or adoption data.

The author states that LoveRace treats finding a partner as a scenario to explore rather than a future to predict. It aims to make visible the scale of one’s search, tradeoffs created by preferences, and assumptions hidden in compatibility claims.

It positions itself as an honest, data-informed tool that answers a different question from typical dating products: “if these assumptions were true, what would the probability model imply?”

The project evolved from a personal spreadsheet idea into a polished public-facing application with statistical rigor and design intent. The author notes that Codex played a central role in shaping both product strategy and implementation.

Not evidenced: No claims about market positioning, branding, or differentiation against competitors beyond self-description.

The description states that the tool is intended for individuals who want to understand how their preferences affect their chances of finding a compatible partner. It targets people who are curious about the math behind dating and want to explore hypothetical scenarios.

It does not appear to target specific demographics or personas beyond those interested in exploring personal compatibility models.

Not evidenced: No segmentation, user personas, or targeting data.

The application is described as free and publicly accessible, hosted via GitHub Pages with no paid hosting or database requirements. The author states that it was built to be open and available to anyone without cost.

There is no indication of monetization, subscriptions, or pricing tiers.

Not evidenced: No business model, revenue streams, or pricing information beyond the fact that it is free.

The application is built with:

• Semantic HTML
• Custom CSS
• Vanilla JavaScript
• No frameworks or build tools
• Uses World Bank API for data
• Hosted on GitHub Pages
• Source code available in a public repository

Codex was used extensively throughout the development process, including:

• Product strategy
• Statistical reasoning
• Design and implementation
• Testing and deployment

The author describes an iterative collaboration where feedback led to changes in UI, methodology, and data handling.

Not evidenced: No details on scalability, performance, or technical architecture beyond basic stack.

The project is described as a publicly released tool, but there is no evidence of:

• User engagement
• Adoption metrics
• Customer feedback
• Retention or usage data

It was submitted to the OpenAI 2026 hackathon, suggesting it may be in early development or prototype stage.

Not evidenced: No traction indicators, user base, or product maturity beyond its release.

The description does not mention any direct competitors. The author states that most dating products focus on displaying profiles and maximizing engagement rather than helping users understand the scale of their search or tradeoffs in preferences.

It is positioned as a data-driven alternative to traditional dating platforms, not necessarily a competitor to other tools but a new kind of experience.

Not evidenced: No competitive analysis, market sizing, or comparison with existing tools.

• Lack of traction: No evidence of user engagement or adoption.
• Unproven utility: The tool is self-reported as useful, but no external validation or feedback exists.
• Data limitations: The model relies on proxies and assumptions due to lack of comprehensive global datasets.
• No monetization strategy: The tool is free and open-source; unclear if there’s a path to revenue.
• Self-reporting only: All claims are unverified, and no third-party data or audits are referenced.

Not evidenced: No risk assessments, financials, or market validation beyond the author's own account.

1. What is the actual user engagement like? Are there any metrics on how many people use it?
2. How do you plan to scale this beyond a single developer’s effort?
3. Is there any intention to monetize or build a sustainable business model?
4. Have you considered how real-world behavior might differ from the assumptions in your model?
5. What are the limitations of the data sources used, and how do they impact accuracy?
6. How does the tool handle edge cases or unusual user inputs?