2026 version of https://manifold.markets/AdamK/will-an-ai-minecraft-agent-defeat-t-a3b3eb99c337
In line with progress in AI Minecraft (https://voyager.minedojo.org/), will there be a public announcement of a fully autonomous AI system which can defeat the Ender Dragon before Jan 1, 2026? To establish an objective baseline of competence and consistency in achieving this task, I'll stipulate that such a system must beat the Ender Dragon in less than 150 minutes of in-game time (deaths allowed) in at least 1% of runs.
Systems which are pretrained on human data are allowed.
The system must only use observational data that includes what a human player would be able to see while playing the game (including the debug screen), like the Minedojo simulator. Systems which have active access to external reference information (like a Wiki) are fine, as long as it does not include additional information on the specific world that the agent is playing in.
1,000
3.00For those who've been tracking this, are there already AI runs which have beat the dragon, but have done so too slowly, or are they not able to achieve the goal regardless of time given?
As a not very good player, I've never beaten the dragon and don't have a good sense of minimum time required. Pretty easy to do in that span of time via "normal" (but motivated) playstyle? Or do you need to employ a speed-runner's approach, by which I mean starting with a plan that is time-optimized and not deviating from it for the whole run?