Skip to content

AI · AI today, November 19, 2026

Science

OpenAI uses its own models to design chips, cutting area by about 13%

· Aster editorial team

Frost crystals branching across a cold window pane.AI-generated image

OpenAI described on November 18 how it uses its own models to design parts of Jalapeño, its chip for running AI. The company says two of the chip's blocks took up about 13% and 10% less silicon area, and work with AMD produced gains of up to 14% over already heavily optimized designs. OpenAI says this delivered roughly a year of progress in under five months. It is also working with Synopsys to train a specialized model.

Why it matters

Smaller, more efficient chips can make AI cheaper to run, and it shows AI helping build the hardware it runs on.

For the technical crowd

Standard-cell area cuts in the warp engine (~13%) and matrix unit (10%). Evaluation covered 9,881 scored runs. Models used include GPT-6.1 Sol and GPT-6.2 Astra.

· Source: OpenAI

More from AI today

See all of the day’s stories · Whole section