Cursor seems to have intentionally dropped semantic/embedding-based codebase indexing. Their explanation is that newer coding agents are now good enough at searching repos directly. They can grep in parallel, inspect directories, read likely files, and refine the search themselves. Cursor says this now works as well or better for most cases. [1]
So the architecture shifted from something like “chunk → embed → vector DB → retrieve” to “local search index/ripgrep → agent explores.” There is still an index, but it’s a conventional local search index. No embeddings are involved in that retrieval path. [1]
The interesting part is that Cursor was still reporting a ~12.5% accuracy gain from semantic indexing in January 2026. [2] So this looks less like “semantic search never worked” and more like agentic search improving fast enough that the extra infrastructure stopped being worth it.
Yes, even my 2013 Haswell-based Arch Linux KDE Desktop feels more responsive than my M4 MacBook. And I think the MacBook has so much more power under the hood, but somehow the animation settings or whatever are just not that good.
To be completely fair, I use the Desktop via DisplayPort at 144 Hz, while the MacBook uses HDMI + USB-C, and I believe it's just at 60 Hz, which is also a factor, but I honestly think that this is not the primary reason.
Crashes?!? I've been using Conversations for a long time and can't remember any crashes. Something must be wrong with your setup.
For me, the bigger problem is that I was unable to get OMEMO + Apple Clients working properly. I think OMEMO 1 has some design flaws and hope that OMEMO 2 will fix those.
Can't all the countries that are hit by US tariffs try to lower the barriers to trading with each other? Not a quick fix, but a signal to the US that they are losing its position in the long term.
This is definitely going on in the background. Mercosur and another EU trade deal with India. Canada and China (which was struck down but I imagine it will be rekindled with this). Just wait for some EU + Canada deal soon enough.
I wonder how many other websites are doing such stuff. Lately, KDE Plasma often shows me that audio is being played by Firefox, but no tab in Firefox has the speaker icon. So far, I have not found which page causes this issue (I don't use AliExpress).
I mean, it should say something like, 'Sure thing, we don't just use cookies for our servers, but to track you through half the internet, to know exactly what you want even before you know it. Please feel free to accept it or piss off.'
I don't like those lawyers either, but they are not the primary problem. The problems are tracking systems that don't just track you across one website but across multiple sites, like those deployed by Google and Facebook. And since Cambridge Analytica, we know that those are not just hypothetical scenarios and that they actually have an impact on elections and where our society is heading.
I solved the issue by building an extra Android Launcher for the kids, where you can add apps and videos, but then you have the problem that you can't configure your own launcher on all tablets (e.g. Fire Tablets).
Nice approach. I chose a web app for the same portability reason: the child signs in once in a browser and KidScreen can be added to the Home Screen. That reduces platform-specific work, but it still does not guarantee that every device or TV browser supports YouTube embeds correctly.
EDIT - AI says:
Cursor seems to have intentionally dropped semantic/embedding-based codebase indexing. Their explanation is that newer coding agents are now good enough at searching repos directly. They can grep in parallel, inspect directories, read likely files, and refine the search themselves. Cursor says this now works as well or better for most cases. [1]
So the architecture shifted from something like “chunk → embed → vector DB → retrieve” to “local search index/ripgrep → agent explores.” There is still an index, but it’s a conventional local search index. No embeddings are involved in that retrieval path. [1]
The interesting part is that Cursor was still reporting a ~12.5% accuracy gain from semantic indexing in January 2026. [2] So this looks less like “semantic search never worked” and more like agentic search improving fast enough that the extra infrastructure stopped being worth it.
[1] https://forum.cursor.com/t/what-do-you-think-about-cursor-re...
[2] https://cursor.com/blog/secure-codebase-indexing
reply