All tech news

HardwareThe New Stack · 1 d ago

Nvidia used 20,000 training examples to fix its AI’s mistakes. Its coding score jumped.

Photo: The New Stack

Nvidia used Factory’s Droid coding-agent harness to generate roughly 20,000 rows of post-training data for Nemotron 3 Ultra, the 550-billion-parameter open model it released in June. Capturing reproducible agent failures In a Wednesday case study, Factory detailed how Nvidia deployed Droid inside an air-gapped network and instrumented the harness to capture reproducible failures in instruction following, tool calling, and error recovery for model post-training.

Droid relies on Nemotron to maintain a structured task plan throughout execution. Factory found problems with tool calls and argument formatting, as well as instances where the model continued working without recovering from errors.

Excerpt from The New Stack, in their own words. Bonzai did not write this story; the full version is on the publisher’s site.