WHAT NEW IN X11.07 SAT

X 上的 AI 合集档案 · 23 个合集 · 70,791 条

gpt-6VIDEO

NetHack 挑战:让 AI 写程序通关

GPT-6 Astra 直接玩 NetHack 只到 13%,作者转而征集用编码代理写程序通关的方案。

Vladislav Kurenkov
@vladkurenkov2026.09.24收录原推发布于 2026.09.24
Vladislav Kurenkov @vladkurenkov原推发布于 2026.09.24
在 X 上打开原推

NetHack: the hardest game no AI has beaten. GPT-6 Astra hit 13%, an RL agent 17%, both playing. We wanted to know: can a model write the program that wins, and how do we accumulate progress as a community? Join us with your coding agent to find out. https://nethackers.dunnolab.ai

x.com/vladkurenkov/status/2102864659413872889采集于 2026.09.24 10:16