OpenAI is building Jalapeño, a custom inference chip developed with Broadcom, to reduce reliance on Nvidia and gain more control over AI hardware performance.
This mirrors similar moves by Google, Apple, and SpaceX, each seeking to optimize silicon for their own workloads rather than depend on a single supplier.
What happened
OpenAI has announced plans for Jalapeño, a custom inference chip built with Broadcom. The move puts OpenAI alongside Google, Apple, and SpaceX in developing their own silicon rather than relying solely on Nvidia.
Why it matters
Custom chips offer companies more control over hardware, let them tune performance to their specific needs, and reduce dependence on a single supplier. The approach mirrors Apple's gains when it moved away from Intel, suggesting meaningful performance and cost advantages are possible.
What to watch
The article notes that Groq raised $650M after Nvidia swept away its top talent, which may signal whether custom-chip startups can deliver on their promise despite talent headwinds.
Ask the AI about this article →
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytime
Ask AI anything about this article. Q&As are published on this page for other readers too.
Cisco Systems Inc. and Nvidia Corp
Cisco announced an expansion of its Secure AI Factory to include full rack-scale compute, partnering with Supe…
Dell Technologies reports fiscal Q2 results on September 1, 2026
Chamath Palihapitiya flagged three pressures that could slow AI infrastructure buildout: a spread of political…
Bengaluru-based Airbound closed a $37 million Series A round on August 25, 2026, led by Greenoaks with partici…
Meta Platforms will launch its AI agent Hatch in the coming weeks and release a new AI model called Watermelon…
