Yesterday, I finally got around to setting Opus 4.8 on the codebase. It was able to find and correct numerous subtle performance issues.
Features I could no longer spend time implementing, it could one-shot in roughly 10 minutes (not without issues). I could also fan out agents to work on multiple things at once.
One thing I found is that the knowledge I gained from doing things by hand greatly helped reject bad AI generated ideas. For example, my game is a starfighter flight sim and one idea was to tick AI collision detection checks lower the further AI ships were away from the player, which for a flight simulator leads to a lot of crashing into the terrain. A great idea for an FPS, but a terrible idea for a flight sim where enemy ships are often very close to the terrain.
My takeaway is that we are in a golden era where we currently have projects that are half human coded, where AI can pickup the slack. But soon we will be in the Dark Ages where AI generates all the code, and the end result will be much worse as the devs begin to lose an understanding of what they are creating.
I feel a solid game engine paired with a good content pipeline can ship games at such a rapid clup that the gameslop gets lost as the noise it is.
The owner of Pinboard has a great story about this:
"I ended up buying a competitor. Why? Because his choice of tech stack + server footprint cost more than mine. The consequence of this was that even with each of us charging the same price. I was profitable and he was not.
Do not try to compete against Pinboard"
I don't know what will happen either. I hope that you and I and other hardworking, basically good people will continue to have a somewhat meaningful, somewhat pleasant existence in the post-AI world, and I think that might be possible, but I just don't know.
> 2012
sigh