@a1zhang : Claude can play Pokemon, but can it play DOOM? With a simple agent, we let VLMs play it, and found Sonnet 3.7 to get the furthest, finding the blue room! Our VideoGameBench (twenty games from the 950s) and agent are open source so you can try it yourself now --> 🧵 • TwiCopy

Alex Zhang

@a1zhang

+ Follow

incoming phd student @MIT_CSAIL, @vant_ai, @princeton ‘24 | 🫵🏻 go participate in the @GPU_MODE kernel competition!!!

ID: 4593727300

linkhttp://alexzhang13.github.io/blog calendar_today24-12-2015 22:30:58

168 Tweet

11,11K Followers

415 Following

Alex Zhang

@a1zhang

2 months ago

Claude can play Pokemon, but can it play DOOM? With a simple agent, we let VLMs play it, and found Sonnet 3.7 to get the furthest, finding the blue room! Our VideoGameBench (twenty games from the 90s) and agent are open source so you can try it yourself now --> 🧵

thumb_up_off_alt416

chat_bubble_outline22

repeat56

shareShare