febed

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

This seems like something that would be very expensive to run. Do you have some representative figures at a particular resolution and frame rate?

It would be helpful if you could add a diagram showing the flow of data. I get the general idea but not how you implemented it.

I’ve been using Obsidian with Dropbox sync for years. What’s so special about the Obsidian sync?

Does it support extensions like PostGIS?

AI is increasing my job security at the moment because the junior developers I work with use AI without discretion. On of them didn’t remember having worked on a feature they built with AI assistance in the recent past. To his credit he admitted he didn’t know how the code worked.

Wouldn’t having a spatial index give you most of the performance gains talked about here without needing H3?

If possible could you share a repo/gist with a working docker example? I’m curious how the instant clone world work there.

My brain interpreted this as the archivist being killed. I’m sure I’m not the only one.

Interesting how Venezuela has more oil than Saudi Arabia but is not able to capitalize on it due to systemic issues

What was your prompt to get it to run the test suite and heal tests at every step? I didn’t see that mentioned in your write up. Also, any specific reason you went with Codex over Claude Code?

Can skills completely replace MCPs? For example, can a skill be configured to launch my local Python program in its own venv. I don’t want Claude to spend time spinning up a runtime

Apart from sounding a bit stiff and informal, I was also surprised at how good Gemini Live mode is in regional Indian languages.

The biggest issue with Windows 11 for me is the noticeable performance lag in basic apps like Notepad and File Explorer. Simple tasks, like opening files or navigating folders, feel sluggish, and I can visibly see windows rendering in slow motion. I’ve heard this might be due to Windows 11’s UI elements being redrawn over lower level UI. I’m considering switching to Linux as my daily driver.