It was inevitable until the point all apps will disappear and AI will be the entry point for all work. You can see how anything required appear based on a single request. After which world models and other forms of interaction that are more dynamic will make sense and we'll need something that's not a screen.

Its a large leap from “we made a config driven diagram tool and trained an llm on that config” to “all apps will disappear”. If you’re predicting such grand claims please be more precise than “AI” which is a term we cant define.

Yeah an app doesn't "disappear" because you put an AI interface in front of it and then use a bunch of old school programming to parse LLM output and feed that into your old app. 99% of the work is still building the old app.

You're harshing the vibe, man.

For sure, leave the hype profiteers alone!

And the people that still get excited about life!

For about a year I've been working on Mu - an app for everything without ads, algorithms or exploits. https://mu.xyz

Blog, news, chat, video, mail, web. Basically all the daily habits as little micro apps in one thing. I find it quite useful. Not sure anyone else does yet though.

Also separately worked on Reminder.dev which is a Quran app and API that bakes in LLM based search and motivational reminders.

Does group AI chat not exist already? I thought this was a thing. It makes sense as a product. Any examples?

Let Claude write the blog post https://go-micro.dev/blog/3

There's still a lot to be said about refinement e.g a lot of inconsistencies or half truths.

Ah yes it was that one cheers

Location: London, UK Remote: Yes Willing to relocate: No Technologies: Go, distributed systems, APIs, etc CV: On request Email: asim@mu.xyz

Most recent work https://mu.xyz Most well known work https://go-micro.dev GitHub profile https://github.com/asim

Every agent I've seen in Go has been so straightforward. Take exe.dev's Shelley. Great example of clean code and very effective tooling. Worth a try if you haven't used it.

This is my gut feeling also. I forked the project and got Claude to rewrite it in Go as a form of exploration. For a long time I've felt smaller useful models could exist and they could also be interconnected and routed via something else if needed but also provide streaming for real time training or evolution. The large scale stuff will be dominated by the huge companies but the "micro" side could be just as valuable.

This is very interesting and timely. I've been working on something to replace a lot of addictive or exploitive services we use today but there's some caveats. Will people pay? They pay for Kagi but will they generally pay for other things like news, maps, video, chat, weather, etc. The second question is what's stopping people from really quitting? I get the feeling it's sort of habits that we get stuck with. Even I still use Google. But the mention of brave and knowing brave has a generous free search tier for their api makes me think it's possible to replace Google search. But habits die hard. New habit formation may require an alternative approach hence so many buying into ChatGPT.

One issue I also find with this sort of thing. It's hard to have a longer discussion that leads to building good alternatives. A thread appears, we comment and then it disappears. There needs to be more public discourse that leads to tangible results... To real issues that get solved.

I'll take it! I've been using Opus 4.6 with GitHub Tasks sparingly but any sort of continued usage is very expensive. This would be handy, like 10x my efforts.