Team post-trains Qwen3.6-35B on 10 B200s in 24h to win poker hackathon, $7500
rhythmrg · x · 2026-11-16
At the ValsAI × Applied Compute hackathon, Nanda Velaga's team post-trained Qwen3.6-35B-A3B on 10 B200 GPUs within 24 hours to play 6-max No-Limit Hold'em, beating every other bot to win the pockerbot track and $7,500.
Organizer Applied Compute framed poker as a hard post-training problem: multiple players, hidden information, and delayed rewards — all under a 24-hour clock. Photos show the team with the champion screen.
More from coding & agent
- Solo dev ships products daily with a Claude + Codex pipeline, 35k users — cneuralnetwork · 2026-11-16
- Kids Build Games and Make Robots Sing at AGNTCon Kids Day with goose AI — steveonjava · 2026-11-16
- Anthropic Academy offers 13 free Claude courses, all with certificates — nikola_mr64990 · 2026-11-16
- Apple's Xcode 27.3 beta adds GitHub Copilot support and in-app Siri AI testing — iamfakhrealam · 2026-11-16
- macOS 27.3 renders Markdown natively in Quick Look; Siri AI skills use SKILL.md — iamfakhrealam · 2026-11-16
- 10 free GitHub courses teach you to build AI agents, from MCP to coding agents — victor_explore · 2026-11-16