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 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 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)
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