DSemba

I'd argue LLMs are getting cheaper, so it will get more feasible for LLMs to soon act on our behalf, bringing only what we're interested in.

Projects like OpenClaw and Hermes already show that this can work whether the source is RSS or simply a website the agent visits.

Even Google now envisions this, since they recently announced "information agents" (https://blog.google/products-and-platforms/products/search/s...) that will keep working in the background. They surely have an index they can use, but I wonder whether that's necessary? AI agents like Claude Code suggest it's possible to use simple keyword searches, without maintaining vector indexes - https://www.tigerdata.com/blog/why-cursor-is-about-to-ditch-...

It could be that soon we're gonna get a fully personalized briefing on the topics that we're interested in, or maybe a new kind of feed, replacing social media.

I'm actually working on the briefing idea myself: https://briefin.com

Thanks :) Each brief brings the stories in the format shown on the page.

I myself tried n8n in the beginning but these workflows get pretty complex pretty quickly.

I actually recently submitted something similar - https://briefin.com/hackernews/

Less like good-old newspaper, but instead made for scannability & readability, with discussion highlights for each story.

Any feedback greatly appreciated!

I once made a slide deck on vector vs keyword search, right when vector dbs were on the rise:

https://vec3.ai/

Seeing the confusion this article caused maybe someone will find it useful.

I see the authors don't argue it well enough, but one could use AI agents with simple grep and that proved to be efficient enough to be the default in Claude Code.

I personally turned of indexing feature in Cursor and I use it without it - I haven't noticed any accuracy drop, though my codebase is not enterprise-size one.

I'm working on https://briefin.com/, which turns any topic into a newsletter.

I wanted to replace those passive social media feeds, where I'm just being served what gets clicks. I completely avoided any embeddings or typical rankings, using ai agents instead, to get precise results and things that are actually interesting to me.

Still working on the platform, but I made a tool that already turns Hacker News into a personalized daily digest here https://briefin.com/hackernews/ (with summaries of the discussions)

Let me know what you think :)

On the other hand, NIMH says 31.1% of U.S. adults have anxiety https://www.nimh.nih.gov/health/statistics/any-anxiety-disor...

at least you know a human wrote it :)