The website design and art are beautiful, well done.

Thanks, really appreciate that!

I'm amazed at the comments on this.

This is really awesome. I've long wanted something like this, especially the local first with p2p sync. Why did you choose nostr over direct p2p with iroh which has dumb relay as fallback?

Would like to join as well if you're willing to share

Usually I bounce between the Zig and Odin discords, as well as the Handmade Network discord.

Agree with your assessment, I think after models reached around Opus 4.5 level, its been almost indistinguishable for most tasks. Intelligence has been commoditized, what's important now is the workflows, prompting, and context management. And that is unique to each model.

Same for me. There are tasks when I want the smartest model. But for a whole lot of tasks I now default to Sonnet, or go with cheaper models like GLM, Kimi, Qwen. DeepSeek hasn't been in the mix for a while because their previous model had started lagging, but will definitely test this one again.

The tricky part is that the "number of tokens to good result" does absolutely vary, and you need a decent harness to make it work without too much manual intervention, so figuring out which model is most cost-effective for which tasks is becoming increasingly hard, but several are cost-effective enough.

This is not true for some cases e.g. there are stark differences in the correctness of answers in certain type of case work.