drewlanenga

access is just part of the larger problem of context curation, but i'm glad to see there beginning to me more consensus around access.

"If you do not have to add back at least 10% of what you removed later on, you clearly did not delete enough".

Looks like they're not even there yet.

no.

the title of the study is :chef-kiss:

the multi-vector duplication thing makes sense, copying every attribute once per vector explodes quickly. what's the new primary index?

On the whole, yes. Antfly can create full-text, semantic, and graph indexes natively, so scaffolding a personal knowledge graph is quite straightforward (and is what SearchAF does). But more to your question about that task list:

- Category 1 (Personal Info): Yes. Especially if you choose to index notes, emails, photos, etc. - Category 2 (Phone & App Control): No. This is what Siri should have been doing all along, and probably not an Antfly task. We'd obviously have less hooks for tool calls than what Apple exposes to Siri internally ("take a selfie") - Category 3 (Internet Queries): Yes. Antfly also has the ability to - Category 4 (Visual Intelligence): Yes. Antfly enables a lot here for multi-modal inference. And intelligence isn't necessarily restricted to Antfly's own inference tools -- SearchAF also ingests image tags classified by Siri. - Category 5 (Screen Intelligence): Yes. Providing image context on-the-fly would come from Antfly's natively embedded inference runtime (which again, all runs on-device).

I've actually been using this to build a local file search agent. I started building it on the Go version of Antfly, but the new Zig runtime is a huge improvement (better resource utilization, reliability, recovery, ...)

Anyone who has used Spotlight search on macOS knows that (1) it can be an absolute resource hog, and (2) it's relatively useless (even with Siri stuff they added in macOS 27). So I was eager to take a stab at a native app that did both better and kept everything on-device (no external inference providers), and building it on Antfly meant I could run it all from one engine (way simpler to coordinate than a whole RAG pipeline).

[Disclaimer: I work at Antfly. The local search app is in preview now at searchaf.com. We plan on open-sourcing it soon (probably with its own Show HN post), as a handy reference architecture.]