Tech stack:

- Rails 8

- Embedded React frontend w/ Tailwind

- Sidekiq for cron jobs

- Perplexity API for story info extraction via URL

- Gemini 2.5 Pro for classifying story extraction results as valid/invalid

- Gemini 2.5 Pro for summarizing stories and HN comment threads (tried Claude but preferred the personality of Gemini surprisingly)

- Cursor with Gemini 2.5 Pro + Claude 3.7 Sonnet for codegen

Could you indulge a bit in describing the workflow?

For example, the "story info extraction" and its "results evaluation" deserve some more in depth explanation.

How do you have the LLM summarize the article and the HN submission page: do you put the whole text in the input (as in: "Summarize the following text: <page text here>")?

Sure thing.

For the story summary: send a prompt to the Perplexity API (which can access URLs) requesting an extraction of the article's content (a sort of very detailed technical brief). Then, use Gemini to classify the results from the Perplexity API as valid or invalid (sometimes, Perplexity isn't able to access the URL but it doesn't reliably return the string I've requested it to return when it isn't). After that, send a more detailed prompt to Gemini requesting the story summary be generated with a specific style and format (Markdown).

For the comments summary: use the HN API to pull all comments, then prepare a Markdown document with a selected subset of comments (based on user karma, replies, and thread depth) if exceeding a given number of comments, otherwise all comments. Annotate comments with an index (eg, 1.1) to indicate the nesting to the LLM. Along with some formatting and stylistic guidance, send that to the LLM requesting summarization.

While the story summaries are generally static once generated, regenerate the comment summaries on an interval (this could be optimized).

Hopefully that helps a little!

I hope the final summary is created by Gemini by having it process the original text, instead of an intermediate from Perplexity...

Notable HN comments page summary excerpt:

> [The] announcement ... stirred up the usual HN mix of excitement, skepticism, and security paranoia

Paranoia does seem a tad strong, doesn't it?

Well we are used to the "best possible interpretation" rule: it will be taken as tongue-in-cheek, jocular rhetoric.

"Ah, the concerns of the involved... Bakers and their care towards flour"

There's probably a bit too much JS for such a site. Is the "challenge" necessary? It will limit the amount of browsers the site will work on.

--

But I would implement a "if landscape, then present list of titles on a left pane, with <a href='#pos'> page positional links to the right pane article stubs" (no JS needed).

Hey mdp, open-sourced it this morning: https://github.com/mzxrai/tinysums

This was a fun little project, but unfortunately can't spend too much time on it. It's also quite expensive to run -- around $15 per day in Gemini summaries (I'm sure 2.5 Flash would be much cheaper, but unsure about the quality)!

Thank you! I had checked your GitHub pages... ;)

I think it was a good idea and implementation; there will be ways to perfect it.

And it will be useful as learning material for other applications.

Indeed, it’s been a fun little project! Just pushed out a new version with 2.5 Flash and tl;dr’s.

Instead of the 'Show more' button, use a link so that one can open the full summary in a new page.

Request: you should also have a feature, "provide a Tinysums page for the input submission" (e.g. "news.ycombinator.com/item?id=43862810").

Cool, but needs a TLDR a top each entry, tiny paragraph.

Added!

Agreed. Great suggestion!