Making games in Go: 3 months without LLMs vs. 3 days with LLMs

LLMs can't help much with assets?

But image generation and cloning a visual artist’s style is one of AI’s apparent strengths.

So it’s interesting to think about what the gaps are between fulfilling a single prompt and completing a project.

This.

You may as well buy a shooter game starter pack or whatever that can save you >1year of coding, no llm needed.

Code is not a hard part.

Making mechanics fun and good assets is what is hard and takes forever.

Sure you can use llm to write a generic game, but its easier to find same game on github and just use that code, why would you write it again with llm.

Why not just copy the mechanics of an existing fun game?

AI generated assets look like dogshit

Many people do and then sell nothing

If it's identical, you made a clone. If it's evenly slightly different, the design needs to be rethought. In a good game, the mechanics, assets, and game loop harmonize. Change one piece, and the balance shifts.

Incidentally so do many cheap games.

Wargroove copied almost everything from advance wars and put it in a fantasy setting, yet it sold much more than most indie games. Copying most values and mechanics from another game wont make a massive hit but it doesn't sell nothing, people who like the mechanics a lot will buy it to play with them some more in a new game.

If you copy a nintendo-platform game which hasnt gotten any love in a long time, put effort into it, and sell it on PC, then yes, you can sell a lot. Harvest Moon hasn't had a good game in over a decade, which is why Stardew Valley was so successful. Similarly, Pokemon has been neglected for generations and there have been a few successful games in the genre, like coromon.

But if you mean copying an already successful PC game with AI Slop assets and putting absolutely no thought into what makes the game good, then you probably should work in a field you actually care about instead