Tag
Development posts tagged agents. Tags cut across the categories, so this pulls together work on the same subject from different parts of the game.
8 posts
A nine faction RTS with a campaign, built in 140 days by one human who has never read the code and one model that wrote all of it. How that actually works.
Capability pays where a change can be wrong in a way nothing would notice. Sort a week of your own work by what would catch it, and the answer is usually the effort setting rather than the model.
642,530 lines directed by someone who has never opened a file. The plan is the interface, and this is what a plan has to contain to be arguable by a reader who cannot check the code.
Parallel agents work well on separate files and fail on shared decisions. Three collisions from building this blog, and the brief shape that prevents them.
A dwarf army, a goblin fortress and the ground under both were built the same afternoon by different sessions. What that buys, and the one rule it cost to learn.
A model starts every session knowing nothing about the last one, so the documentation is the memory. That changes what belongs in it, and it is rarely a diagram.
Rewriting the pathfinder under an army of wargs meant comparing 18,000 routes against the old one. That only happens if each run starts without approval.
A language model gives orders every 12.5 seconds while an autopilot handles the second-by-second work. Where the boundary sits, and what it costs to run.
