What is the parameter count for the famous proprietary models like gpt 4o and claude 3.5 sonnet?
What is the parameter count for the famous proprietary models like gpt 4o and claude 3.5 sonnet?
The shameful answer is that the most convenient method of setting up immich is a docker compose stack but I have podman installed instead.
WOW man this is just incredible. I had actually finished setting up syncthing and syncing with it but this is just so much smoother. Syncthing is nice but it has some weirdness. Like this app’s “copy local to remote” (instead of sync) is hidden in advanced configuration while it seems like a useful use case to be.
I tried one distro and now the other distros confuse and scare me.
I am not really concerned with which one is better or smarter but with which one is more resource intensive. There is a lot of opacity about the cost in a holistic sense. For example, a recent mini model from OpenAI is the cheapest smart (whatever that may mean) model available right now. I wanna know if the low cost is a product of selling on a loss or low profit margin, or of an abundance of VC money and things like that.