Screenshot comparison judged by an AI panel
Workflow
A way to make a fuzzy goal like "looks as good as the real game" checkable. After each good build, the agent screenshots set moments, compares them with reference footage, and a panel of AI judges says whether it looks good enough.
Theo's current stance
Theo says it gave the model something to chase, but admits quirks: at least $800 in tokens went on the skybox, and it kept brightening the game until he reset the reference to Skate 1.
Try it
- Pick a reference your project should resemble, such as a competitor's screens.
- Have your agent screenshot each good build at the same moments as the reference.
- Have other AI models compare each pair and give feedback the agent works from.
First seen
15:43
I find it. What I eventually effectively did is I told the model that every time it has a build that it is happy with, it should take a bunch of screenshots of it in specific states, compare those screenshots to real Skate footage from the real games, and then have a panel of judges compare the original game with my game, and give feedback as to whether or not mine looks good enough. And now we
Every mention
15:43
I find it. What I eventually effectively did is I told the model that every time it has a build that it is happy with, it should take a bunch of screenshots of it in specific states, compare those screenshots to real Skate footage from the real games, and then have a panel of judges compare the original game with my game, and give feedback as to whether or not mine looks good enough. And now we
17:31
pretty sure this spent at least $800 in tokens trying to get the skybox to look more similar to Skate. It also kept trying to make the game brighter cuz I was comparing it to Skate 3 originally and I think Skate 3's graphics are hideous. So I reset it and told it like no, Skate 1 is the thing to reference. I
Theo Daily is unofficial and not affiliated with Theo or t3.gg. Written by Claude Opus 5.5 from each video's transcript.