GPT‑5.3‑Codex‑Spark

Re:GPT‑5.3‑Codex‑Spark by kumarvvr on Thursday February 12, 2026 @08:19PM (#46997738)

Is this actually beneficial than, say having a bunch of smaller ones communicating on a bus? Apart from space constraints that is.

[ Parent | on HN ]

Re:GPT‑5.3‑Codex‑Spark by zamadatix on Thursday February 12, 2026 @08:38PM (#46997880)

It's a single wafer, not a single compute core. A familiar equivalent might be putting 192 cores in a single Epyc CPU (or, more to be more technically accurate, the group of cores in a single CCD) rather than trying to interconnect 192 separate single core CPUs externally with each other.

[ Parent | on HN ]

Re:GPT‑5.3‑Codex‑Spark by santaboom on Thursday February 12, 2026 @08:38PM (#46997878)

Yes, bandwidth within a chip is much higher than on a bus.

[ Parent | on HN ]