I think that's part of it, but then the user perceives "personality changes" when the model changes due to differences in the model. Now they have lost their relationship because of the model change.
Anyone attempting to build a movement might find it interesting how Pumping Station One in Chicago is governed. It's a maker space but run by people who care (at least from my experience when I was a member back in 2015/2016). The process for electing leadership and holding members accountable was very democratic and fair, from my experience. They open-source as much as they can about how they organize:
Microsoft Teams was bad, so they rebuilt it and somehow made it worse. Then they decided to do the same with other apps, like Notepad. I switched to Ubuntu on my computer this week. Linux administration is not something I want to spend time on, but LLMs are able to help me debug why my password manager can't talk to my browser and write shell scripts to fix it... I'm able to focus on work and be done with the Microslop.
There are a lot of Android devices that look temping until one discovers how out-of-date the firmware is.
With no option to install your own, of course. Boot loaders should be exclusively for running the manufacturer's lone security update from 5 years ago.
I do this with Chrome recording and Playwright. What I need is an AI agent to meander through my product as if it were the target user and test/break things so I can pass that to my LLM to fix. Does anyone have that?
Different from our core use case, but our agents can do open-ended exploration as well. You could prompt something like "navigate to this app as a new user and try common. flows" with structured outputs for findings. Session recording will show what happened. Not sure if it fully solves your problem - but happy to explore this together if you want to try it.
reply