News for hackers. Stuff that matters.

A comment on OpenAI and Broadcom unveil LLM-optimized inference chip. Parent comment

Re:OpenAI and Broadcom unveil LLM-optimized inference chip by kccqzy on Wednesday June 24, 2026 @07:22PM (#48666761)
My hunch is that this change is driven by bean counters.
[ Parent | on HN ]
Re:OpenAI and Broadcom unveil LLM-optimized inference chip by amelius on Thursday June 25, 2026 @07:44AM (#48672005)
Who says Google isn't doing its own designs mostly?
[ Parent | on HN ]
Re:OpenAI and Broadcom unveil LLM-optimized inference chip by kccqzy on Thursday June 25, 2026 @08:40AM (#48672482)
Oh they definitely are. But as a transitional step, replacing Broadcom with MediaTek is probably mostly about cost.
[ Parent | on HN ]