ansipunk
Re:We ran AI agent swarms in Minecraft and Mindustry
on Friday October 30, 2026 @08:49AM (#50303168)
Oh, my bad then.
Re:We ran AI agent swarms in Minecraft and Mindustry
on Friday October 30, 2026 @08:23AM (#50302947)
Moreover, in their private training sessions, their models played cumulatively about 180 years worth of games, so I doubt there were many mechanics left to be mastered.
Re:We ran AI agent swarms in Minecraft and Mindustry
on Friday October 30, 2026 @08:14AM (#50302870)
I don’t think they did. If I remember correctly, the only limitation they have introduced was the available playable character pool.
Re:We ran AI agent swarms in Minecraft and Mindustry
on Friday October 30, 2026 @01:59AM (#50300343)
No image recognition, the bot gathers info about the game from Dota's developer API. Which, to be fair, is a massive advantage, but it, in my opinion, doesn't make the achievement any less.
Re:We ran AI agent swarms in Minecraft and Mindustry
on Friday October 30, 2026 @01:29AM (#50300175)
That's what I said in my comment, that LLM is just not what you want for such a task.
Re:We ran AI agent swarms in Minecraft and Mindustry
on Friday October 30, 2026 @01:11AM (#50300064)
It is impressive, but it is also a display that LLMs are simply not suited for this, there's way too much latency. Obviously, a more specialized neural network would be much better, but would you believe this:
In 2017, OpenAI presented the first version of their program that plays Dota 2, a very complex, fast MOBA with endless mechanics and defeated one of the world champions in a one-on-one match. Next year, they showed the world OpenAI Five, a version of the program, that runs a full five player team of those bots and they managed to defeat a full team of world champions in 2019. They ran an event where the bots would play for 4 days straight and they won 99.4% of 42,729 matches.