@maximelabonne: No items, Fox only, Final Destination achieved internally d1 2-stocked a LVL 9 Fox and even trolls it with fox-trotting…
Summary
Maxime Labonne shares a demo of an AI agent playing Super Smash Bros and beating a Level 9 CPU Fox two stocks on Final Destination in real time through an API, highlighting advances in real-time agentic gaming.
View Cached Full Text
Cached at: 10/01/26, 08:19 AM
No items, Fox only, Final Destination achieved internally
d1 2-stocked a LVL 9 Fox and even trolls it with fox-trotting. This is real-time through our API. https://t.co/DSgj1dAOVf
Similar Articles
@maximelabonne: What is happening? d1 is not trained on it and the prompt is not even optimized yet. No item, Fox vs. Falco LVL 7, Fina…
Maxime Labonne expresses surprise at an AI agent (d1) performing impressively in Super Smash Bros. Melee (Fox vs. Falco on Final Destination) without being trained on the game or prompt optimization.
@10xmylife: cool 啊
An AI system named 'jev' is showcased playing Super Smash Bros. against itself, controlling multiple characters and making rapid decisions within fractions of a second, using over 22 million tokens.
@no_stp_on_snek: Ran this on Laguna S 2.1 in Poolside's own agent (pool), pointed at a local instance on a DGX Spark, using the prompt l…
A comparison of two AI coding agents building a Mario game: Laguna S 2.1 in Poolside's agent took 62 minutes with self-correction and passed tests, while a previous Qwen model took hours and needed human help; highlights oracle discipline and native harness advantages.
@MTSlive: Osmantic founder @TheAhmadOsman demos a hack-and-slash game his local agent built end-to-end on the RTX Spark without e…
Osmantic founder Ahmad Osman demos an offline local AI agent named Portal that built a full hack-and-slash dungeon crawler end-to-end on the RTX Spark without internet access, highlighting how fast local agent capabilities have advanced.
@maximelabonne: You can play all these games in parallel with one model This is much bigger than text generation with LLMs for the vide…
Maxime Labonne highlights a single model capable of playing multiple games in parallel, suggesting AI advances that go well beyond text generation for the video game industry.