Skip to content
HomeNewsConceptsGuidesToolbox
AboutSubscribeUA
Subscribe

AI Today Brief

The daily AI-engineering brief. Built in public. EN · UA.

XTelegramLinkedInYouTubeRSS

Follow AI Today Brief on LinkedIn for daily AI-engineering updates and the weekly “5 shifts that changed how developers work” PDF.

Explore

NewsDigestsConceptsGuides

Company

SubscribeAdvertiseAbout

Legal

Editorial policyAI disclosurePrivacyTerms

© 2026 AI Today Brief. All rights reserved.

  1. Home/
  2. News/
  3. Vibe coding workflow/
  4. Simon Willison Benchmarks Codex Desktop Sub-Agents in 3D Game Vibe Coding
Vibe coding workflow

Simon Willison Benchmarks Codex Desktop Sub-Agents in 3D Game Vibe Coding

August 8, 2026· 3 min read
OKCurated by Oleksandr Kuzmenko, AI Product Engineer·Updated August 8, 2026·Sources cited on every story
AI-assisted · editor-reviewed·How we use AI
Simon Willison Benchmarks Codex Desktop Sub-Agents in 3D Game Vibe Coding

Simon Willison tested Codex Desktop using GPT-5.6 Sol Ultra in aggressive sub-agent mode to construct a complete 3D web game from a single prompt. While Codex coordinated sub-agents and generated visual assets using gpt-image-2, it failed to fix visual rendering bugs during screenshot self-inspection.

Impact: Medium

Why it matters

Understand the current performance limits and visual inspection failures of multi-agent execution loops in vibe-coding workflows.

TL;DR

  • 01Sub-agent orchestration handles multi-file asset and logic generation effectively
  • 02Vision-based self-correction in agent loops still misses prominent visual bugs
  • 03Inspect full transcript logs to evaluate sub-agent decision paths and API call costs

Key facts

52 minutesExecution Time
gpt-image-2Asset Model
Execution Time
52 minutes
Primary Model
GPT-5.6 Sol Ultra
Asset Model
gpt-image-2

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
#Codex Desktop#GPT-5.6 Sol Ultra#Claude Fable 5#gpt-image-2#Codex

Sources

  • Moonlight & Mayhem Blog Post by Simon Willison
ShareShare on XShare on LinkedIn
← Previous storyClaude Code Switches to Auto Mode Default with Layered Injection DefensesNext story →Allen Institute Releases TutorMoments Framework for AI Agent Evaluation

Related stories

  • Vibe coding workflowBuilding Location-Aware Applications via Claude CLI Vibe Coding
  • Vibe coding workflowRust Monorepo Formulates Policy for AI Code Contributions and PR Reviews
  • Vibe coding workflowPrevent Cognitive Debt by Retyping Agent-Generated Code Manually
  • Vibe coding workflowRethinking LLM Co-Authorship and Developer Accountability in Pull Requests

Email digest

Get the morning AI brief

One email a day — the stories that matter for engineers, founders and tech leads. Human-edited, with links to primary sources.

  • ✓120+ sources scanned daily
  • ✓Edited by a human
  • ✓1 email per day
  • ✓EN + UA

By subscribing you agree to the privacy policy.