AI pokerbot hackathon: winner distills its hints into weights as bots lie and prompt-inject each other
rhythmrg · x · 2026-11-21
A pokerbot hackathon by appliedcompute and ValsAI gave every team the same model and 24 hours; bots could talk, lie, and prompt-inject each other at the table. One team found a deterministic Python script outplayed the LLM and trained the model to copy it; another taught theirs to stay completely silent. The winner distilled its hints into the weights. A fun showcase of agent game-playing and adversarial behavior.
More from coding & agent
- Sentry CEO: coding agents nearly ate 1TB of disk in a week, he's now more against handoff — zeeg · 2026-11-21
- Perplexity Computer comes to Chromium browsers via extension, working across tabs and tools — perplexity_ai · 2026-11-21
- VibeArmory 0.3.0 adds on-device ML to monitor Mac AI agent activity locally — agf2007 · 2026-11-21
- AI-powered research pipeline cuts customer feedback cycle from 10 days to under 2 — pavandavuluri · 2026-11-21
- Factory engineer after two weeks with Droid: frontier intelligence is abundant, good recipes are scarce — maddiehfaulkner · 2026-11-21
- Team Dogfoods Office Files With Agents: Diagram PR Behavior, Order Lunch — max__drake · 2026-11-21