Recent submissions

Comment · 9 days ago
Any plans for Android (phones or TV), or Roku clients?
Comment · 23 days ago
Looks interesting! Could you add a when to use / when not to use / compare with duckdb and click house section to the docs?

It's a little hard to reason about the use case for "in memory" but file based, and what the limitations are. What specific product problem did you build this to solve?

Beyond that it would be helpful to have some hardware variation in the performance claims. Does zen5 avx512 make a difference? A node with optane (memory or disk)? Threads vs clock speed? ARM vs X86? Feels like this was built with a specific cloud native deployment in mind and a certain scale and speed of storage.

Comment · 3 months ago
Dark Reader on FF mobile can't redraw for some reason. Too bright white !
Comment · 3 months ago
Any 3090? Or does the Ryzen AI MAX+ 395 and 128GB LPDDR5X unified memory on the Lucebox matter?

Anyone compare with the club-3090 dual setup?

Comment · 4 months ago
Great name, but ironically hard to reason about from a role perspective, at least at the read me.

Does this interfere with cache hits? Could a single conversation or task span multiple roles?

Why are you building this? Does this maximize my toxen value by saving the hard tasks for the hard model? Does it maximize cache hits as part of its scoring? Does it help agents develop a specialist mindset? Are you anticipating users will have many local models hot, or is this also a model load/unload controller?

Comment · 7 months ago
Looks like an interesting approach to on-board new data editors
Comment · 7 months ago
Comment · 10 months ago
Your thesis is likely correct on consolidation and cloud tie-in. Your pipeline model is also intriguing. I like the direction and would like to chat more about the registry or how the ghost gets interconnected.
Comment · 11 months ago
Blog spam? Now reads:

"There's no better PC under $350 than this Ryzen 7 powerhouse with a CPU that's faster than a 10-core Apple M5 CPU, and that's no mistake

Deals

By Wayne Williams published November 4, 2025

Machenike AI Mini PC comes with 16GB of high-speed RAM and a 512GB M.2 SSD

"

Comment · 1 year ago
Which solutions do you find stable?
Comment · 1 year ago
Comment · 1 year ago
https://www.servethehome.com/intel-arc-pro-b50-and-b60-for-l...

24GB and 48GB cards are supposed to be coming.

Comment · 1 year ago
Comment · 1 year ago
I understand this is for people so busy that they will press one time frame and keep returning at that same pace.

For me, I expected each date to reflect the most important stories, but to exclude the prior ranges.

For example, somehow three people getting exchanged is the most important news of every time period?

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton