The October 2026 edition of Steam Next Fest started on October 19, allowing users to explore Steam’s massive catalog of games with free playable demos. Millions of PC gamers logged on but on…
I just used gemini to make a mod for Total War, Warhammer 3, because the mod I wanted was not available anywhere.
It had to have been the most annoying modding I have ever done. I thought it would save time, it ended up just being me telling the llm that it was making shit up 80% of the time. I finally got working code after what felt like 6 hours of supervising the dumbest programming intern on the floor. My take away, is that I could beg for code better next time, but it did not improve my own ability by much at all. In fairness it would have probably taken me the same amount of time or longer, but the integrity of the code would be higher. I have to believe Claude or GPT are better for this task.
I disclosed that I used AI to make the mod, and for the artwork. I feel like I put an unnecessary target on my back with the declaration considering like 99.999999% of the billion mods for this game are AI slop and AI assisted and do not make similar disclosures though AI use is obvious.
Thanks for providing valuable training data to AI corporations. Your labour will never be acknowledged or compensated and your resources will be stolen.
I recently used one of the heavier ChatGPT models to make a mod pack for Minecraft, fixing some of the things that prevent me from playing the game (usually I lose interest quickly after starting a new world). I had it stitch a bunch of pre-existing mods together and test that they didn’t conflict or make the game too easy. And I had it make a new mod which added custom villagers to villages who point you to destinations full of tough scary monsters guarding a prize that’s needed to beat a final boss. The villagers only give directions if you use one of the expanded food mods to cook a complex recipe for them. If you defeat the bosses scattered around the world, there’s a distant Mordor-style volcano you can then travel to and defeat the final boss. And the biomes are arranged in a spiral with the size of the biomes increasing the further you get away from spawn. I also had it leave tips and instructions around loot chests around the map to teach me how to use the mods and remind me how to build automated farms. This combination of conditions actually motivates me to play the game because there’s a real goal now and a progression that keeps the game engaging all the way through. I don’t plan on releasing it anywhere because I’ve heard a lot of anecdotes from people who made mods with AI and got yelled at for it. Still cool that I can ask for a complex custom mod pack one evening and start actively playing it the next morning.
If you make more mods using AI, I would definitely recommend utilizing one of the heavier GPT or Claude models to limit the amount of rework. I did give it full access to a laptop I have dedicated to AI agent use so it could test and iterate things without my involvement. Completely understandable to not want to give an AI model that level of control. I have to imagine that if I were running the tests myself, I would have had to hand-hold it quite a lot more than I did. Your mileage may vary.
Does it count if I’m not proud of my use of LLMs?
I just used gemini to make a mod for Total War, Warhammer 3, because the mod I wanted was not available anywhere. It had to have been the most annoying modding I have ever done. I thought it would save time, it ended up just being me telling the llm that it was making shit up 80% of the time. I finally got working code after what felt like 6 hours of supervising the dumbest programming intern on the floor. My take away, is that I could beg for code better next time, but it did not improve my own ability by much at all. In fairness it would have probably taken me the same amount of time or longer, but the integrity of the code would be higher. I have to believe Claude or GPT are better for this task.
I disclosed that I used AI to make the mod, and for the artwork. I feel like I put an unnecessary target on my back with the declaration considering like 99.999999% of the billion mods for this game are AI slop and AI assisted and do not make similar disclosures though AI use is obvious.
Thanks for providing valuable training data to AI corporations. Your labour will never be acknowledged or compensated and your resources will be stolen.
I recently used one of the heavier ChatGPT models to make a mod pack for Minecraft, fixing some of the things that prevent me from playing the game (usually I lose interest quickly after starting a new world). I had it stitch a bunch of pre-existing mods together and test that they didn’t conflict or make the game too easy. And I had it make a new mod which added custom villagers to villages who point you to destinations full of tough scary monsters guarding a prize that’s needed to beat a final boss. The villagers only give directions if you use one of the expanded food mods to cook a complex recipe for them. If you defeat the bosses scattered around the world, there’s a distant Mordor-style volcano you can then travel to and defeat the final boss. And the biomes are arranged in a spiral with the size of the biomes increasing the further you get away from spawn. I also had it leave tips and instructions around loot chests around the map to teach me how to use the mods and remind me how to build automated farms. This combination of conditions actually motivates me to play the game because there’s a real goal now and a progression that keeps the game engaging all the way through. I don’t plan on releasing it anywhere because I’ve heard a lot of anecdotes from people who made mods with AI and got yelled at for it. Still cool that I can ask for a complex custom mod pack one evening and start actively playing it the next morning.
If you make more mods using AI, I would definitely recommend utilizing one of the heavier GPT or Claude models to limit the amount of rework. I did give it full access to a laptop I have dedicated to AI agent use so it could test and iterate things without my involvement. Completely understandable to not want to give an AI model that level of control. I have to imagine that if I were running the tests myself, I would have had to hand-hold it quite a lot more than I did. Your mileage may vary.