Using the Kelly objective in RL destroys your network at ruin: 'ultimate doomer algorithm'
rosstaylor90 · x · 2026-10-27
Ross Taylor shares a counterintuitive RL detail: use the Kelly objective directly and ruin (advantage -∞) destroys your neural network through optimization. It 'hates ruin so much it will destroy your network to stop it ever happening again'—the ultimate doomer algorithm. Funny, but a real gotcha for objective design.
Related event: Researcher: Use CRRA Instead of Kelly for Ruin-Averse RL(3 posts)→
More from Fun
- New AI-industry meme: score figures by their worst take on dating — NathanpmYoung · 2026-10-28
- AI circle meme: unleashing an 'Adam Smasher agent' to hunt down your Claude — tekbog · 2026-10-28
- Hobbyist builds 'Sandman' bot fleet dashboard to gamify context management — alexcovo_eth · 2026-10-28
- Fold your phone into 'tent mode' for an auto-updating training metrics dashboard — wandb · 2026-10-28
- Seedance 2.5 + Suno V6 + GPT team up for a meme MV remix: "More RAM, less scam!" — ivan_bezdomny · 2026-10-28
- Gemini 4 Argon reportedly dominating arena on day 1, but naming unverified — my_cat_can_code · 2026-10-28