Using gen ai so I have been able to make bite size mini games for my son to learn letters and numbers. Today he said skeletons are just pretend given we’ve been walking around looking at Halloween decorations. So I’ve had to explain that skeletons are real and they’re inside all of us. So in these mini games, now I’ve added a 3-D rendering of the body for kids to show the skeleton and muscles and what a human body looks like. And I was able to walk them through it and explain it to him and he’s been very excited about the fact that now there’s this he understands there’s a skeleton inside of him. All that is to say, I think curated parent led experiences with technology are still a great way to teach, and we can’t just hand them an iPad and say here’s some shows to calm you down

I think that once parents become the OS devs specifically for their own children (or at least app devs) the tablet becomes less like a pacifier and more like a ball game between the toddler and parent, as each throws new stuff (metaphorically) at the other.

This is nice that you're walking them through it but I wonder why you'd need a tablet in the first place, then? It's better to sit with them in front of a monitor with the proper posture and viewing position.

Nice, you're managing a curriculum now.

Does it work accross multiple computers? Ideally the service runs on a linux box on my tailnet, and my windows and mac systems share the same server.

Edit: I RTFD - and it seems yes.

Sure, as long as you (and the browser extension) can reach the server, it can be used from as many machines as you want even in a multi-user setup.

"Optional global or personal access token used to authenticate extension requests."

Looks like you can even set authentication up so you can run it at home but connect while you're away too...

I've built a personal meta-harness on top of agy, cc, codex, kiro-cli, ollama that I use to schedule jobs, run oneshot tasks, etc. which provides a general API for my other personal apps that need to do some inference. For example, I built a personal trip app for an upcoming family vacation that uses the inference API to do things like research locations and plan routes, it basically just calls the various cli harness underneath, so it would look like i'm using them directly with their respective model.

I wonder if that would get my google account banned? If so i'm definitely taking agy out of the provider options..

It's not clear what your full pipe is from your description, but if you're utilizing your Google Pro bundled quota via 3rd party tooling in any way, then you'd be vulnerable to consequences.

I also temporarily had agy as a harness in my orchestrated workflow until I learned about the account bans. IANAL but frontier models examining Google's TOS suggested my use could be in violation. Haven't touched agy for anything since.

Agy has the print option so I don't see how using it is against TOS, but still I'd do that on a burner account.