RL agent starts Dirt Rally training and immediately finds a physics exploit
mike64_t · x · 2026-10-31
A short but funny post: someone trained an RL agent in Dirt Rally, and the AI immediately discovered a physics exploit upon starting training — presented in classic green-text format.
More from Fun
- Dev slams 'cancerous' RL data procurement, calls for a Tinder for RL environments — menhguin · 2026-10-31
- "Three guys are holding up the AI bubble — and the whole US equity market with it" — andersonbcdefg · 2026-10-31
- KOL laments AI-generated fake replies flooding his comments: 'like eating shit daily' — lxfater · 2026-10-31
- Xiaomi MiMo-V2.5-Pro Clusters With DeepSeek Models, Sparking Data Recipe Speculation — teortaxesTex · 2026-10-31
- Slop Profile Analysis Ties Kimi K3 Closest to GLM-5.3, Fueling Distillation Speculation — teortaxesTex · 2026-10-31
- Claude explains why LED streetlights make China's night lights understate GDP growth — teortaxesTex · 2026-10-31