This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Will Held
williamheld.com
did:plc:exj4ro3xzv7id2hstt5ys5j5
There were two red flags in the runs from that initial sweep: suspiciously large weight norms and learning rates!
For the first, I switched to Kaiyue Wen's Hyperball optimizers.
For the second, I found the answer in Apple's Complete(d)P paper: arxiv.org/abs/2512.22382
https://arxiv.org/abs/2512.22382
2026-05-11T19:59:51.269Z