Google's $916 agent-built operating system claim lacks key methodology details

Google claimed a team of agents built an operating system from a single prompt for about $916 in API fees, using Gemini 3.5 Flash and Antigravity 2.0.

The authors argue the prompt was many thousands of lines, the scaffold and human intervention are undefined, and no code, logs, or similarity analysis were released to verify the claim.

They still see value in such open-world evaluations, which need stronger methodological norms and independent scrutiny.