Nvidia: AI agent failures may stem from harness or runtime, not the model

Nvidia says AI agent failures should be viewed as a system problem, with causes possibly in the harness or runtime rather than the model. The company is developing the OpenShell runtime and launched the SAFE initiative with about 140 companies to share agent failure data.

• Top coding agents fail over 60% of tasks on real codebases
• SAFE failure-reporting initiative backed by about 140 companies
• Monitoring adds roughly 20% to OpenAI inference compute costs
• Nvidia splits the agent stack into model, harness and OpenShell runtime