menubar VS yazz

been working on https://github.com/smol-ai/menubar for a couple months, but nervous to "launch" it because i feel like it hasn't had a significant "wow" moment yet. basically the idea is to 5x the amount of chat output for every unit of human input, to get variety + familiarity with the wide range of chat models out there. its moved from a "smol menubar app" towards its own "ai chat browser". i wonder if i should put int he work to make it a full "ai browser" before i launch it.

comparing them every day via https://github.com/smol-ai/menubar . i'd say when it comes to coding I pick their suggestions about 30% of the time. not SOTA, but pretty darn good!

fwiw i noticed the demo failing before today's release. i use all 4 major chat apps every single day for every query (https://github.com/smol-ai/menubar) and started detecting a major major regression in bard about a week or so ago. so suspected something was going on, went back to pop in this question and lo and behold

smol-ai/menubar: a menubar with Zero latency access to ChatGPT/Bard/Claude! A/B test them, or use them in the background. I use this 20 times a day. (github.com) It has a customizable URL. But I don't know how to install it. Plus limited to three chatbots.

smol menubar - quickly access ChatGPT, Bard, and Anthropic with a single keyboard shortcut

i think the best way to consume these things is a menubar app that can be brought up quickly with a shortcut. i recently released https://github.com/smol-ai/menubar which i personally use!

smol ai enjoyers may also like my other app https://github.com/smol-ai/menubar/

Shameless plug. My own one of course :)

https://github.com/yazz/yazz

You can also try one I am building, a cross between Visual Basic and Microsoft Access here:

https://yazz.com/

i am working on such a thing myself at https://github.com/yazz/yazz. Also there are many other people trying to build something similar

I keep hacking away on Yazz for over 10 years now.... even if there is zero payoff I keep hacking... and that is what hackers do... we are not doing for the money... https://github.com/yazz/yazz

I really loved this talk and feel for Evan. As someone who was a VC/Angel investor in the space (I was the initial angel investor for something called LightTable/Eve) back in the day, worked for a couple of years at Red Hat, and am working on my own Open Source Language here: https://github.com/yazz/yazz (so yes, you could say I am a VC trying to build a low code product with my own hands), so I feel I have a valid opinions on this. I think that it is possible to make money in opensource as a little guy, but you need to have a combination of consulting, hosting, and support services. If your product is not able to encapsulate being sold and packaged as something that is possible to demo and sell to customers then you will most likely struggle to make a living from it

I am actually trying to make an open source successor, but using Javascript instead of Basic, at https://github.com/yazz/yazz and a demo at yazz.com

I'm still building a low code system with an easy to use component marketplace where you can edit components within the low code tool. Still a work in progress: https://github.com/yazz/yazz

Author of a framework that also stores it's code in IPFS for easy sharing (https://github.com/yazz/yazz). ScrapScript is a really nice concept with how it stores code. I originally got the idea for storing the code as a hash of the contents from Unison, and it looks like the idea is really starting to catch on with more and more languages now. Well done!

I’m working on a low core project that is already using content addressable source code that is stored in IPFS at https://github.com/yazz/yazz so it can be done

There are already some Dbos type systems out there. I built one which stores program state in SQLite databases and process state and programs are also stored in SQLite. In the oat I believe things like silver stream did the same too. The project I made is open source too: https://github.com/yazz/yazz