You can read the entire article without that, it explains everything really well.
It’s not like many companies in the world where the video IS the article and they just assume no one reads.
You can read the entire article without that, it explains everything really well.
It’s not like many companies in the world where the video IS the article and they just assume no one reads.
The article looks LLM-ey, which was really off putting for otherwise interesting content.
"If the model predicts wrong on your filaments, that’s a data problem, not a model problem. We need more measurements."
…
"… there’s a real path to a proper perceptual colorspace model in the spirit of Mixbox or Spectral.js – predictions that are correct by construction across the full ratio space, not patches on residuals. None of this is hard. The math exists. It’s a data problem."
…
"Not in some distant future. Now. The hardware exists. The slicers exist. The filaments exist."