A case has been revealed in which Anthropic’s Claude Opus 5 implemented a playable first-person shooter game with only a short, three-paragraph prompt, widening debate over how to design prompts for artificial intelligence coding. On July 28 local time, blockchain outlet Decrypt reported that AI investor and former Hyperlight CEO Matt Shumer released a video showing the model building the game on its own, without external assets, just 2 days after Claude Opus 5 was launched. The prompt posted on GitHub consists of three short paragraphs, instructing the model to make a shooter game at a “Call of Duty” level, split the work across multiple sub-agents, and have a separate harsh critique agent blind-compare each output against actual gameplay footage. The process used Claude Code features, and an “ultracode” setting let the model set its own execution plan and distribute work across up to 16 agents. The finished game runs on a Three.js and WebGL2 base, with code totaling about 55,000 lines divided into 11 subsystems. However, the critique log shows the score rose from 3.59 out of 10 to just over the 5-point range, but “Call of Duty” remained ahead in every recorded round. Former hedge fund manager James Altucher said he used the same prompt to make “Operation Blackout” with a little over 10 hours and about 1.3 million tokens.