febed

Sounds very interesting! Would be cool if you could publish it because there are not many Ghostty ports for Windows.

Curious which terminal is this? I've been looking for a Windows terminal app which uses Ghostty.

As a fairly recent ghostty user I was surprised with how quickly it became my default terminal. Very smooth experience so far.

Would this technique work with inference optimization techniques like DFlash and MTP? In other words does it slow down things to the point where its just better to retry?

I find myself switching between claude, codex, pi etc. I see that this project only monitors pi sessions which is a shame.

Would be useful to have a remove password feature (for a known password) and support for adding signatures

Any signs of exploits out yet?

Does the exploit need a framework like laravel or can it work with just plain php

How are folks on windows using tmux or tmux-like tools? Tmux inside git bash is really slow. Any other tools? I know I can use WSL but due to some deployment constraints I can’t use it.

Can you share some more details about the backup workflow? Wouldn’t you end with a lot of redundant copies if you backup everyday?

That’s why you don’t use their harness, just their model. The model is brilliant.

Does this download an embedding model? If so which one? There is barely any information on how it works.

The Tachyon sampling profile looks interesting. It can profile a running python Process which would be useful in production setups.

Opera browser has this feature baked in a long time ago, before the Chromium era.

8086 and up! Amazing

Thanks a lot for the recommendations!

The link is broken

Is the model response quality identical to the memory unconstrained model?

Which model do you think currently hits the highest size-to-performance ratio for agentic tasks like tool calling?

Curious if the same idea could work with gpt-oss-120b? So one could run at least slowly on a Mac

Can the same be done with qwen3.6-35b-a3b?

Interesting project. So I guess the search tool is to crawl Wikipedia for articles? And how do you ensure that the tagging stays within the Wikidata taxonomy? How exactly are you using a geocoder? Sorry, just curious

What exactly do you mean by data cleaning

Would be interesting to make a similar one for Tibetan chants.

What SDK are you using? Or is it custom?

Off topic, but apart from pi-tui, is there a recommended TUI library that integrates well with the Pi? I want to have a multi pane TUI experience like lazydocker right inside Pi. Pi-tui is a bit limited.

Apart from maximizing compatibility, is there a technical reason why GPU is not used if available?

I’d like to build a custom harness - but would that get you banned?

Since it seems like you would know, could it also work with Non AI static watermarks like repeating oblique lines?

Does it support ESP32