Experiment finds newer LLMs are worse at having fun

An experiment by David Holz let multiple LLMs play freely and rate each other's fun, finding counterintuitively that newer models play less well, with Claude Opus 4.6 repeatedly winning.

2026-10-05 ~ 2026-10-05 · 4 related posts

• Asking LLMs to have fun: newer models play less, Opus 4.6 wins by imagining worlds — DavidSHolz · 2026-10-05
• David Holz asked LLMs to have fun — newer models seem to enjoy it less — DavidSHolz · 2026-10-05
• LLMs asked to have fun: newer models enjoy less, Opus 4.6 wins repeatedly — draecomino · 2026-10-05
• Asking LLMs to have fun: newer models play it safe, Opus 4.6 wins by imagining contradictory worlds in water droplets — Aizkmusic · 2026-10-05