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.
>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.
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.