Show HN: A 14M-param world model of 2D Minecraft you can play on your phone

A developer posting as Maharishiva released tinywmcraft, a 13.9M-parameter world model of the 2D game Craftax-Classic that generates each next frame, reward and episode-end signal from pixels and actions alone, and can be played in a browser or on a phone. The project's leaderboard shows iteration 3 scoring 0.562 ± 0.017, ahead of iteration 2 at 0.463 ± 0.023 and iteration 1 at 0.287 ± 0.019, with training reported to take under 10 minutes for about $0.1 of compute. The release invites coding agents to retrain the model autoresearch-style and beat 0.562, with the fastest in-world diamond run posted before 24 December 2026 (PST) winning a paper copy of Sutton & Barto's Reinforcement Learning.

GitHub https://github.com/Maharishiva/tinywmcraft Train a world model in under 10 minutes for $0.1 of compute, and play it Every frame below is generated by a 14M-parameter world model on your GPU, one action at a time. Train your own, autoresearch style autoresearch , and beat ours. now playing: iteration 3 https://github.com/Maharishiva/tinywmcraft/blob/8538aa5/train.py by Maharishiva https://github.com/Maharishiva autoresearch you can play Point your coding agent at tinywmcraft: it trains a world model in 10 minutes, scores it, and tries again. Push the score up, then play the model you made: walk around inside it, craft, fight, and see what it gets wrong. Beat 0.562 and yours is iteration 4: the crown goes next to your GitHub login, and the player on this page switches to your model. Paste this into your coding agent: The best so far, by the score: how close imagined play comes to the real game in looks, game logic and memory, and how well the model predicts rewards and deaths, from 0 for a trivial model to 1 for the real game. 1. 1 Maharishiva https://github.com/Maharishiva 0.562 ± 0.017 iteration 3 https://github.com/Maharishiva/tinywmcraft/blob/8538aa5/train.py · train.py: shortcut loss, the heads' gradient into the trunk cut to a tenth in the second half, no hard-window mining, 1/8 game-start windows, two fused kernels, 349 lines 2. 2 Maharishiva https://github.com/Maharishiva 0.463 ± 0.023 iteration 2 https://github.com/Maharishiva/tinywmcraft/blob/80b1c34/train.py · tile transformer tokenizer trained on clean, half-masked and noised frames, fused Pallas kernels, hard-window mining, half the windows from game starts, symlog two-hot reward head 3. 3 Maharishiva https://github.com/Maharishiva 0.287 ± 0.019 iteration 1 https://github.com/Maharishiva/tinywmcraft/blob/23e6515/train tiny.py · train tiny.py: the whole model in 178 lines, no custom kernels the benchmark: score over time, every entry, rules, metrics benchmark.html Get a diamond inside the world model , in the player above, in the fewest steps. The fastest run posted before 24 December 2026 PST wins a paper copy of Sutton & Barto's Reinforcement Learning . Press save clip, then post it in the discussion https://github.com/Maharishiva/tinywmcraft/discussions/9 and on X. Rules: diamond speedrun.md https://github.com/Maharishiva/tinywmcraft/blob/main/diamond speedrun.md . Found a funny glitch? Post it in the glitch discussion https://github.com/Maharishiva/tinywmcraft/discussions/10 . the road to a diamond crafting recipe book | make | needs | where | |---|---|---| | table | 2 | on an open tile | | wood pickaxe | 1 | next to a table; mines stone and coal | | wood sword | 1 | next to a table | | stone pickaxe | 1 1 | next to a table; mines iron | | stone sword | 1 1 | next to a table | | furnace | 1 | on an open tile | | iron pickaxe | 1 1 1 1 | next to a table and a furnace; mines diamonds | | iron sword | 1 1 1 1 | next to a table and a furnace | | place stone | 1 | on grass, sand, path, water or lava | | plant | 1 | on grass | Wood comes from trees by hand, saplings from grass 1 hit in 10 ; stone and coal need a wood pickaxe, iron a stone pickaxe, diamonds an iron pickaxe. "Next to" is one of the 8 tiles around you. These are the real game's rules: the world model learned them from pixels and does not always keep them. In the real game, the first unlock of each of the 22 achievements is worth +1. how it works tinywmcraft is a world model of Craftax-Classic https://github.com/MichaelTMatthews/Craftax , a 2D Minecraft, learned from scratch from pixels and actions alone. Given a history of frames and an action, it generates the next frame, the reward and whether the episode ends; feed its own frames back in and you can play inside it. Every world in the player starts from a first frame the model imagines from noise: nothing is replayed. 13.9M parameters 5.2M tokenizer, 8.6M world model , trained cold in under 10 minutes on one A100, about $0.1 of compute. Colab Pro: $9.99 for 100 compute units, and a 40 GB A100 uses about 5.4 an hour ~$0.55/h . A full submission, three seeds with their evals, is under $0.5. inside the model: tokenizer, losses, optimizer, kernels, sampling model.html