I use claude in my games(Currently a hobby) I draw a character on paper, claude models the proportions symmetrically and then I go back in and slowly build up the model. I wouldn't have a problem with artists doing this at all, in fact I don't know of a good reason not to. However if they generated a picture, sent that to claude, took whatever claude generated and threw it into the game then its going to look like garbage and cause they didn't start by throwing new information into the system it must start from training data so it will look the same as all the other slop.

That first step of starting with a piece of paper or some human seed is huge, the more detailed that step the less I care about the rest of the process.

I could see myself printing all sorts of costumes for it and using it as an ad hoc characters for tabletop games or as a spare bandmate if I ever finish my synth.

"We make money by selling the hardware for $1,688, with optional paid software on top."

The software would have to be quite good and also affordable for me to consider it, as all subscriptions are liabilities. I might one day want my robot to go with me to a show or to do something meaningful. Whenever that happens I will NOT be held hostage by software and will either source my own software or replace parts of the hardware till something works before I keep throwing money at a bad service. I would prefer to just have a good vendor supported software that I don't have to think about but I have trust issues. Privacy would be a huge concern, I can't have this in my garage lab with all my stuff being sent back to your servers for computer vision tasks etc.

I also bought some cheap gloves from harbor freight and used a needle to route fiber through each finger to make a simple power glove like thing which I think I can connect to arm arm to make a cool robot game. I think of the two I am more excited for the first but its much more work than the second and my day job is getting more exciting than I would like so by the end of the month I'll have had to pick one to finish.

Email is more than a technology its a community. There have been plenty of technical attempts at replacing it but they have failed to un-seat email because they focus only on the technology aspect which as you have found is largely a solved problem although... getting the details right might be hard. You need buy in from the community which is not just users but also businesses and organizations that use email which is everyone from CEOs to church leaders. It's not enough to fix email you have to get buy in from the community to make a meaningful change and I don't see anything here that would do that. This isn't really a criticism, just an insight I offer. I work in this field and we're trying to get out of it cause managing email sucks. I would love something new to take its place but the community has heard so many promises that never came to fruition, when that happens you either need a better promise(harder than it seems) or you need credibility which may be very difficult in the current climate. Not an unsolvable problem, those don't exist but sometimes the lever you need to solve the problem is further than you can reach alone and this is one of those times.

I think of my agents like golems from disc world, they are defined by their script. Adding texture to them improves the results so I usually keep a running tally of what they have worked on and add that to the header. They are a prompt in a folder that a script loops over and sends to gemeni(spawning an agent and moving to the next golem script)

I also was curious to see if it could be used it for developing some small games, whenever I would run into a problem I couldn't be bothered to solve or needed a variety of something I would let a few llms work on it so in the morning I had something to bounce off. I had pretty good success with this for RTS games and shooting games where variety is something well documented and creativity is allowed. I imagine there could be a use here, I've been calling it dredging cause I imagine myself casting a net down into the slop to find valuables.

I did have an idea where all my sites and UI would be checked against some UI heuristic like Oregon State's inclusivity heuristic but results have been mixed so far. The initial reports are fine, the implementation plans are ok but it seems like the loop of examine, fix, examine... has too much drift? That does seem solvable but I have a concern that this is like two lines that never touch but get closer as you approach infinity.

There is some usefulness in running these guys all night but I'm still figuring out when its useful and when its a waste of resources.

Escape rooms are honestly... almost always a let down but the concept has a lot of potential and there are some really neat ones that standout like this local one where you pilot an airship https://www.portlandescaperooms.com/steampunk-airship

Once I build the best escape room on the planet, I can consider selling the tools.