Here’s the result of my second run with Codex.
The first run turned a reference image into an interactive 3D container-terminal simulation. This time, I asked Codex to audit the system in depth, suggest improvements, and implement them.
Harbor now includes:
- An experiment lab for saving runs and comparing scenarios against a baseline
- Repeatable experiments with matched random seeds across scenarios
- Timeline replay and branching, so you can rewind, change settings, and explore a different outcome
- Individual container tracking, with a journey history from ship to yard
- Yard-crane capacity, queues, and shared-road reservations
- Diagnostics showing why cranes and vehicles are waiting
You can test whether adding vehicles actually improves throughput, see where queues build up, and compare the results of different operating settings. You can also return to an earlier point in a run, change your decisions, and save the new result for comparison.
The second pass also improved the rendering, controls, and layout, with clearer cargo stages and completion milestones.
Learning
One port photo became a 3D container terminal simulator in the browser
Junho Yeo gave ChatGPT a single image of a container port and got Harbor: quay cranes unload a ship, vehicles carry boxes to the yard and a dashboard tracks throughput. A second Codex pass added repeatable experiments, timeline rewind and branching, and per-container journey histories.
312likes
18reposts
337saves
18Kviews
- Posted








