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.
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.
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.
But if you look at minecraft interacting with other Humans in an Environment where there is no winning requires some part that is capable of natural Language.
Also it is more an interesting way to see how different architectures behave
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.
https://en.wikipedia.org/wiki/OpenAI_Five