The verdict: pi plus a basic searxng skill outperformed Local Deep Research. Also, pi is just much more configurable: I can easily just tell it to use not just internet searches, but also my own world_knowledge directory.
His write-up of the local-first, privacy-hardened LLM setup he actually runs — hardware, models, agent tooling and sandboxing.
As it turned out, ollama was not able to fit Qwen3.5:35B onto my GPU, but llama-server could. Hence, from that day forward, I resolved to cease being a cave-dwelling noob, and use llama-server (via llama-swap to make model swapping easier).
I gave pi a skill for using the search engine SearXNG (which aggregates many search engines together at the same time), and one for calling into a daemon that I wrote that gives it access to read my email and Signal messages, and send-to-self, and send to others only with human confirmation.
I used ollama before, but when I admitted to this in public half of Twitter told me that I was a noob and llama-server was clearly better and I must have been living in a very deep cave if I did not already know that. I tested their theory.
Its responses are, in my view, pretty bland and not very high-quality. I did a side-by-side test of asking Local Deep Research a question, then asking pi the same question (telling it to use searxng to make as many internet searches as needed), and I fed both outputs into an LLM to ask which is better.
I was not impressed with the DGX Spark; it's described as an "AI supercomputer on your desk" but in reality it has lower tokens/sec than a good laptop GPU - and on top of that, you have to figure out the networking details of how to connect to it from your actual work device etc.
Every entry is a verbatim quote and a link to the public post it came from. Nothing is paraphrased. If it is not on record somewhere public, it is not here.
The verdict is what they actually said: loved and liked are explicit; recommended means they told others to get it; uses means they only say they use it; read is a book on their public shelf with no verdict; mixed and disliked are kept too.
A dashed affiliate link, sponsored or their own label means the post disclosed a relationship. It is shown, never hidden.
The shading behind a date shows how dated a recommendation is for its kind of thing.
The shading behind a date shows how dated a recommendation is, for its kind of thing. Fully green is recent. It drains a quarter at a time as the post gets older, and is empty once it reads as dated.
What counts as old depends on the thing. A laptop praised four years ago has been replaced twice; a book loved twenty years ago is probably still loved. The shading is gone after about:
Hardware, services4 years
Software5 years
Podcasts, courses, other8 years
Books25 years
Stripes mean the post carries no date and the date shown is an estimate. No date at all, no shading.