Seth Karten(@sethkarten):Training VLMs to use vision-only inputs to play games is not just limited to Anthropic. We showed this was possible using Qwen3-VL-Instruct-8b prior to Fable 5 beating pokemon firered. It is great to see a scaled up version in the latest Claude release

2026.06.09 21:36

Training VLMs to use vision-only inputs to play games is not just limited to Anthropic. We showed this was possible using Qwen3-VL-Instruct-8b prior to Fable 5 beating pokemon firered. It is great to see a scaled up version in the latest Claude release

Chengshuai Shi@chengshuai_shi

2026.06.09 21:24

Wondering how VLMs can be trained to play games using only visual inputs, like Anthropic’s newly released Claude Fable 5? Check out our recent work, Odysseus: In Odysseus, we train VLMs to play games directly from visual inputs, using Super Mario Land as a testbed, and scale RL to improve their long-horizon decision-making capabilities. Excited to see more exploration in this direction!