# From Hacker News threads to PG Finds

After reading [Andrej Karpathy’s original post about HackerTube](https://karpathy.bearblog.dev/hacker-tube/), I wanted to try the same idea for PostgreSQL: turn useful recommendations buried in Hacker News discussions into something easy to browse.

The result is [PG Finds](https://albedoweb.github.io/pg-finds/) — **263 articles, tools, guides, and other resources**, each linked to its original source and the HN conversations where it appeared.

![PG Finds: topic filters, search, and resource cards with links to original sources and Hacker News discussions.](https://cdn.hashnode.com/uploads/gql/6aefe354f8418419009a8845/732db8ca-194e-4b15-805d-3eed6b6983c8.png)

## What you can do

- **Find something to read:** search the catalogue and filter by topic, format, or HN mention year.
- **See why it’s included:** each resource has a short description and its own page.
- **Go straight to the source:** open the original article, documentation, or project.
- **Follow the conversation:** jump back to the Hacker News discussions for context.
- **Save things for later:** keep a reading list in your browser, without creating an account.

The catalogue is a static site hosted on GitHub Pages. Its [site source is public](https://github.com/albedoweb/pg-finds).

## The agent team

I used several agents with different jobs:

- **Astra — coordination.** The more expensive lead agent planned the work, delegated tasks, reviewed results, and brought the pieces together.
- **Luna and Terra — implementation and testing.** Cheaper agents worked on data processing, site development, review, and browser testing of the catalogue.
- **DeepSeek Flash — analysis and selection.** It screened candidates in batches and reviewed extracted source text to help classify and annotate useful material.

My role was to set the direction, try the results, and ask for changes. Using smaller agents for focused tasks kept the lead agent available for decisions and coordination.

## How it worked

**Collect → Select → Build → Test**

1. **Collect.** Start with the open [Hacker News archive](https://huggingface.co/datasets/open-index/hacker-news), find PostgreSQL-related links, and preserve their discussion context. I began with 2024, then expanded to 2023, 2025, and the available part of 2026, supplemented by recent HN search results.
2. **Select.** Remove duplicates, prioritize recent material, check links, and review promising pages. Agents produced short descriptions and flagged uncertain dates or project status.
3. **Build.** Turn the selected resources into searchable cards with source links, HN references, and a reading list.
4. **Test.** Use separate agents to check the catalogue in a browser, report issues, and record an acceptance-test scenario for future changes.

The input covered about **15.1 million HN records**; the catalogue grew from 27 pilot entries to 263 resources. This was automated filtering and review, not millions of articles read by me. Coverage is selective, especially for 2026.

Recorded DeepSeek calls cost about **$0.49**. That is a partial processing cost: Astra, Luna, Terra, and some interrupted calls are excluded.

I’ll explore the collection’s statistics in a separate post. For now, [browse PG Finds](https://albedoweb.github.io/pg-finds/) and see what catches your interest.

Thanks to the original authors and Hacker News contributors. The source archive uses the [ODC Attribution License](https://opendatacommons.org/licenses/by/1-0/). PG Finds is independent and is not affiliated with Hacker News.