I am hunting for houses - I've used it as an assistant that catalogs them (but it has this stored in multiple places and will give me the wrong list a lot). I also had it read through my emails and create a doc with my upcoming trips.

I'd say it's right on the edge of being useful, but given the number of bugs, it's not really that practically useful. It's moreso a glimpse into the future.

I have it installed in a VM, and overall it's fairly useful, but very buggy. Right now I can send it a message asking it something, and it won't answer. I typically have to follow up 2 or 3 times before I get an actual response. This weirdly used to work fine.

More broadly, I'd say if you don't have something to retire to (kids or otherwise), don't.

I've found this to be the case as well. My typical workflow is:

1. Have the ai come up with an implementation plan based on my requirements

2. Iterate on the implementation plan / tweak as needed, and write it to a markdown file

3. Have it implement the above plan based on the markdown file.

On projects where we split up the task into well defined, smaller tickets, this works pretty well. For larger stuff that is less well defined, I do feel like it's less efficient, but to be fair, I am also less efficient when building this stuff myself. For both humans and robots, smaller, well defined tickets are better for both development and code review.

> It even has a sprinkle of the silly "wow very technology!" aesthetic pandering that's typical of EVs.

I've never heard it referred to that way, but you nailed the description.