←back to thread

Show HN: HomeBrew HN – Generate personal context for content ranking

(www.hackernews.coffee)
122 points azath92 | 3 comments | 03 Jul 25 12:27 UTC | HN request time: 0.708s | source

TLDR: Build a quick HN profile to see how little context LLMs need to personalise your feed. Rate 30 posts once, get a permanent ranked homepage you can return to.

Our goal was to build a tool that allowed us to test a range of "personal contexts" on a very focused everyday use case for us, reading HN!

We are exploring use of personal context with LLMs, specifically what kind of data, how much, and with how much additional effort on the user’s part was needed to get decent results. The test tool was a bit of fun on its own so we re-skinned it and decided to post it here.

First time posting anything on HN but folks at work encouraged me to drop a link. Keen on feedback or other interesting projects thinking about bootstrapping personal context for LLM workflows!

Show context
pxc ◴[03 Jul 25 18:22 UTC] No.44457835[source]▶
As it is currently written, this is less useful the more niche your interests are. I think for such users, looking at their comment history or upvoted history might be useful instead of or in addition to just sampling recent, popular articles.

In my case, none of the topics I most like to read about and discuss on HN (package management, software freedom, next-gen CLI tools, next-gen shells, philosophy, desktop Linux, functional programming, hacker history, literate programming, Emacs, bitching about common development practices, programming language design, configuration languages) managed to appear in the 30-post sample I used. The profile it wrote for me was pretty good considering that, but definitely not great.

The assessment was also mistaken about my degree of interest in "low level" technical details like binary file formats (in fact it's rather low, although it has gradually increased over time), and my degree of interest in theoretical computer science issues (in fact it's high, but all of the theoretical papers in the sample were about machine learning, which was not an area of academic focus for me).

I do really like the simplicity and customizability of this (exposing the profile as Markdown and making it editable is awesome), and the quality of the results is very good given the tiny input size. But if your primary interests are not super aligned with the mainstream on HN, you won't get a chance to demonstrate that you like them. If users could type a few terms to say what their biggest interests are before running through the samples, this could work even better for people like me.

It would also be interesting if this could work based on article contents and not just headlines. Sometimes I open something and close it immediately, or I open it undecided as to whether I will skim or read closely.

replies(1): >>44459504 #
1. azath92 ◴[03 Jul 25 21:57 UTC] No.44459504[source]▶
This is great to hear in such detial. One of the first cabs of the rank to improve this would be greater user control over what preferences to include, and/or smarter selection of the pool to select. This kind of focused preference is super important, especially as i use hackernews, and clearly for you and i suspect others as well.

In fact I would pose that I have a couple of disparate interests or "profiles" that i would like to have greater control over/support in generating, that are non overlapping sets of topics and types of content. The ability to have greater agency in creating them and managing them is something we are keen to explore.

The article comments one is a toughie, as LLM use skyrockets when you scrape and consume content from the links. It would be awesome to include it, but would likely need to be paid, just from a cost perspective.

Really appreciate the detail here, this makes it easier to turn your examples into a test/eval/feature case.

replies(1): >>44459825 #
2. pxc ◴[03 Jul 25 23:00 UTC] No.44459825[source]▶
>I have a couple of disparate interests or "profiles" that i would like to have greater control over/support in generating, that are non overlapping sets of topics and types of content

This sounds like a great feature! My appetites for different clusters content certainly vary according to my mood! Perhaps "mood" would actually be a cute-but-clear name for such distinct/multiple profiles. :)

> The article comments one is a toughie, as LLM use skyrockets when you scrape and consume content from the links. It would be awesome to include it, but would likely need to be paid, just from a cost perspective.

Hm. That is a good (and in retrospect, obvious) point. If it makes the feed a lot better, I think it could certainly be worth it for some users. If it only makes a small difference, maybe not. It might be interesting for you to experiment and write about, since what kind of difference it will make isn't obvious (at least to me) up front.

replies(1): >>44464911 #
3. azath92 ◴[04 Jul 25 14:33 UTC] No.44464911[source]▶
yeah we are thinking a lot right now about good language for how to separate the notion of a "profile" as representative of who i am, from the concept of a profile that represents what mode im currently operating in right now. In the context of browsing, mood actually captures it quite well i agree. As we think wider to the different ways we might want a profile to help guide what content we receive or results we get when using other tools, that language isnt quite so clear yet.

We will have to do some combo of much more internal testing, construct evals, or just capture more info about peoples usage coupled with an ability to provide feedback in order to even get a handle of such a nuanced thing as "good" with a tool like this. Likely info capture and user feedback would be a first port of call for a substantive change, internal testing is always ongoing, but such a low sample size.