fassssst

Well you could ask it to only reply with snippets from its sources.

Yea but rendering a book’s worth of that, with text selection and embedded web content, is not trivial with the native UI frameworks like it is with web UI.

What’s stopping you from creating a plugin (MCP or Skill) that acts as a subagent? The plugin could use a local model.

Because web sites have always been about rendering huge scrollable amounts of text and images

AppKit and SwiftUI and WinUI are all meh for rendering lots of text. Chromium is quite good at it.

Plus they have lots of embedded web content these days and managing webviews is a relative pain vs it all being one webview

a TAM that consists almost solely of developers

That’s the wrong assumption. These models are good at office docs too.

Why does the code need to be maintainable by humans?

The trick is to have 5 of those huge plans running in parallel.

Chromium has had an insane amount of investment from many large companies. Way more than native UI frameworks have had over the last decade or so.

You can also link directly to a web installer so customers don’t even have to ever see the Store app. The Store provides you a web link for a tiny exe installer, like this: https://developers.openai.com/codex/app/windows

fwiw you can ship through Microsoft Store for free and not have to pay for signing.

Object model

It’s because they embrace their coding models to ship new things at light speed.

It’s web. Just use electron or Tauri.

https://github.com/ahujasid/ableton-mcp

None, you’re on your own. The Browser Company made bindings for WinRT so you can use WinUI imperatively but it’s non trivial to set up.

We use a family paper calendar and I use my watch to check the weather and reminders. Still allows my phone to live in a box at home.

Because it doesn’t matter. The biggest AI apps of last year were command line interfaces for cripes sake. Functionality and rapid iteration is more important.

If only AI had more Liquid Glass, lol

You can also install visual studio build tools via the built in winget package manager.

Why would you want to do that? Outlook is perfectly fine, and on Windows it’s easy enough to toggle between the two windows.

I hate Slack. Total information overload. I’d prefer a tool that encourages people to think more before hitting send.

The base models reportedly can tell Joe Schmoe how to build biological weapons. See “Biosafety”

Some sort of guardrails seem sane.

Nothing

Related: ChatGPT Canvas apps can send/receive MIDI in desktop Chrome. A little easter egg. You can use it to quickly whip up an app that controls GarageBand or Ableton or your op-1 or whatever.

It can also just make sounds with tone.js directly.

That’s ChatGPT Pulse

It’s easy to use

Post training can make known formats more reliable.

Color is cultural. Red is associated with good in China

Yes, the post training is the special sauce.

This is already how it works on Windows, and it is definitely the best path to happiness for all.

Actually Windows has a newish independent text scale accessibility setting that is different than display scale.

Yea, sometimes you have to update your UI to account for that, but it’s not a big deal most of the time.

https://learn.microsoft.com/en-us/windows/apps/develop/input...