Hacker News
points by MatthiasPortzel 5 hours ago | 0 comments
People have done experiments like this before.

Minecraft isn't a intelligence problem. An LLM is more than smart enough to play Minecraft. It's a robotic problem. Even a normal human player can click several times per second, can press two different buttons at the same time, etc. Mineflayer gives you an API that is more limited than a human in some ways (can't see far away from you) and less limited in others (can see through blocks) (if I remember correctly, I could be thinking of Baritone or a different project). Robotics or playing a video game requires a tight continuous feedback loop. When there's 500ms of latency in order to ask the model for every mouse movement, it's no wonder fighting a spider is scary.

Fun fact, Mineflayer, the Minecraft bot interaction API used by YCombinator for these tests, was originally developed by Andrew Kelley (before he started Zig).

[–] 1e1a 2 hours ago
Mineflayer does not strictly limit view distance, you just have to change the setting for it from the default value.
[–] shepherdjerred 1 hour ago
Use traditional game AI for the micro, LLMs for the macro
[–] bombcar 2 hours ago
Get the LLMs playing GT:NH.
[–] teaearlgraycold 5 hours ago
The human body has the ability to automate some muscular movements so the brain is out of the loop. Maybe these LLMs should be allowed to write in a small DSL that can trigger events out-of-band (something like "Oh fuck there's a spider, I'll set up a click spam loop and check in every 500ms").
[–] peri-cl 4 hours ago
I think they're doing exactly what you propose? Unless I'm misunderstanding what the Python "fishing scripts" with the timings and timeouts are doing.

https://labs.ycombinator.com/projects/games/index.html#fishi...