GPT‑5.3‑Codex‑Spark

Re:GPT‑5.3‑Codex‑Spark by odiroot on Friday February 13, 2026 @09:08AM (#47002880)

I can imagine how terribly bad their yield must be. One little mistake and the whole "chip" is a goner.

[ Parent | on HN ]

Re:GPT‑5.3‑Codex‑Spark by tshaddox on Friday February 13, 2026 @09:19AM (#47003052)

They have a blog post called "100x Defect Tolerance: How Cerebras Solved the Yield Problem":

https://www.cerebras.ai/blog/100x-defect-tolerance-how-cereb...

[ Parent | on HN ]

Re:GPT‑5.3‑Codex‑Spark by svnt on Friday February 13, 2026 @10:35AM (#47003868)

One thing is really bothering me: they show these tiny cores, but in the wafer comparison image, they chose to show their full chip as a square bounded by the circle of the wafer. Even the prior GPU arch tiled into the arcs of the circle. What gives?

[ Parent | on HN ]