Oleksandr Kuzmenko, EditorPublished 3 min readAI-assisted · editor-reviewed
TL;DR
- Sub-agent orchestration handles multi-file asset and logic generation effectively
- Vision-based self-correction in agent loops still misses prominent visual bugs
- Inspect full transcript logs to evaluate sub-agent decision paths and API call costs
Key facts
- Execution Time
- 52 minutes
- Primary Model
- GPT-5.6 Sol Ultra
- Asset Model
- gpt-image-2
Source: Key facts — Execution Time
Source: Key facts. Execution Time: 52 minutes. Each figure is copied from the story.
- Execution Time52 minutes
Multi-Agent Game Generation
Simon Willison published a project breakdown comparing Claude Fable 5 and Codex Desktop running GPT-5.6 Sol Ultra. Posing a complex single-prompt game specification, Codex operated in aggressive sub-agent mode to coordinate repository creation, gameplay logic, and texture generation via gpt-image-2 over a 52-minute session.
Vision Inspection Limits
While the sub-agent architecture successfully assembled multi-character stacking mechanics and 3D museum environments, it exposed limitations in automated visual inspection. Codex took and analyzed application screenshots during iteration but failed to detect enlarged black eye spheres floating over the models.
When to use
- One-shot prototyping of complex interactive applications and visual assets
- Parallelizing code generation, graphics scripting, and boilerplate test setup
When NOT to use
- Relying solely on visual agent inspection for UI/UX validation
- Unattended production code deployments without automated continuous integration passes
What to do today
- Review Simon Willison's public Codex transcript to evaluate sub-agent task prompts
- Implement explicit unit test assertions for visual properties when relying on coding agents
Step names are taken from What to do today.
Step names are taken from What to do today. Review Simon Willison's public Codex transcript to evaluate sub-agent task prompts. Implement explicit unit test assertions for visual properties when relying on coding agents
- Review Simon Willison's public Codex transcript to evaluate sub-agent task prompts
- Implement explicit unit test assertions for visual properties when relying on coding agents