AI Foresights — A New Dawn Is Here
Back to homemake money

How OpenAI Used Its Own LLMs to Design Its Jalapeño Chip

IEEE Spectrum AI Matthew S. Smith September 14, 2026
How OpenAI Used Its Own LLMs to Design Its Jalapeño Chip
AI Summary— plain English for professionals

# OpenAI Built Its Own AI Chip—With Help From Its Own AI OpenAI has released Jalapeño, a custom computer chip designed to run AI systems faster and cheaper than chips from competitors like Nvidia. The company used its own AI language models to speed up the design process, cutting what normally takes years down to just 20 months, which suggests that AI tools could soon make chip design much quicker and easier across the industry.

On 25 August, OpenAI fully unveiled Jalapeño, the company’s debut AI accelerator chip. Jalapeño delivers up to 13.4 petaflops of 4-bit compute and accesses 232 gigabytes of the most advanced memory available, linking to it at a blazing 15.4 terabytes per second. Benchmarks cited by OpenAI show that

Read full article on IEEE Spectrum AI

Get new guides every week

Real AI income strategies, tool reviews, and plain-English news — free in your inbox.

or enter email