Test of 37 AI Novels Finds 8k Context Cuts Repetition to 0.5%

Jessica K. Murray generated 37 complete novels using 8 local models across 3 computers, finding that "bigger isn't better." Lowering the context window to 8k cut repetition from 42.8% to 0.5%, far outperforming 32k context, with the full methodology published.

2026-10-12 ~ 2026-10-12 · 2 related posts

• 37 AI novels tested: 8k context cuts repetition from 42.8% to 0.5% — lmoroney · 2026-10-12
• Original writeup: 37 AI novel runs show smaller context windows win — lmoroney · 2026-10-12