NetHackers is an open challenge to build the first program to win NetHack 3.6.6, a 37-year-old game requiring descent through procedurally generated levels and escape under permadeath conditions. No autonomous program has ever achieved ascension on the modern version, though recent reinforcement learning agents have doubled previous progression records. The project invites researchers to use hand-coding, AI agents, and iterative improvement to tackle this unsolved frontier in AI generalization.
GPT-6 Astra became the first LLM to achieve an ascension in NetHack, completing the game on September 21 after 37,140 turns as a dwarven Valkyrie. The agent built its own interface and harness rather than relying on pre-written code, demonstrating that LLMs can bridge the gap between possessing game knowledge and reliably executing it over long decision sequences.
GPT-6 Astra became the first recorded LLM to ascend NetHack, completing the game as a dwarven Valkyrie on September 21 after 37,140 turns. Unlike previous approaches requiring handcrafted interfaces, Astra built its own harness autonomously, demonstrating that LLMs can apply game knowledge through iterative problem-solving and software engineering.