It could actually be fun if done right.

The worst way to do it would be to have people randomly having their characters farming stuff automatically with AI, and users have no way of telling who is AI and who isnt.

But there are plenty of times where a player would love something in the game that was smarter than an NPC, but less important than another user. It would be fun to fill out your raid group or party with a few automated players when you can't fill it for real. Or be able to summon an AI controlled character to duel any time you wanted to practice. It would have to be managed by blizzard and the AI characters would need to be visually distinguished in game, of course.

We’re speed running getting the llms to do all the fun so that we can all go live under a bridge.

Well Twitter and almost any other social network has a lot of AI players and it’s no fun at all …

Right? I love playing games with more computer players and less real people. Really makes games more fun! In fact it saves the need to have an internet connection you can just spawn up a million bots and play on your own. Maybe its full circle just going back to C&C vs many computers.

I've always thought playing ANY game would be a lot more fun with AI npcs. Ever since Todd Howard promised we could affect Skyrim's economy (which was a lie) I've always been hoping for dynamic systems in games for npc behaviour.

Like so many games when npcs have one canned voice line, or the level is lined with doors that won't open because it's not the way you're meant to go.

Last weekend, I made Claude play Panzer General II. I am pretty sure it will be in the weights soon, so it was valuable as an environment the LLM is not trained for. It accumulated experience in Markdown, made some tools to parse the game data and it got to a decent level of skill. It reached the last battle.

I tried to make it win the last battle, but that was beyond its ability. Further accumulation of "hard earned lessons" in Markdown only made its behavior more chaotic.

Still, a very decent result, comparable to what I achieved back in the day (late 90s).

Accessibility api?

> I was initially skeptical that this would work. And if it did, it would require hours to complete with dead ends along the way.

> But it turns out it completed the task easily in 40 minutes with 0 deaths and minimal complications.