Exploring LLM Free Association: Deliberate Typos and Omissions to Spark Ideas
yungcontent · x · 2026-08-24
A user shared a favorite AI use case: being intentionally obtuse and leaving out huge swaths of phrases or completions to see what dots the LLM tries to connect next. Noting that some users avoid even the smallest typos to save tokens, this user maximizes typos to induce "'07 Weezy levels of free association" from the model.
More from Fun
- AI sparks renaissance for new SNES retro games — AIandDesign · 2026-08-24
- Detailed prompt for creating 'Rubber Stamp Travel Field Notes' with AI — AndyMasley · 2026-08-24
- AI Scientists Quitting or Donating Wealth Amid Extinction Fears Sparks Skepticism — Miles_Brundage · 2026-08-24
- Satirical site 'Wheel of Paid Mediocrity' mocks marketing spend — talkaboutdesign · 2026-08-24
- 'Don't Make Fun of Renowned Dan Brown': A Classic Satire Goes Viral — NathanpmYoung · 2026-08-24
- AI Domain Flipper Makes $190K with Outbid, Users Call It Absurd — talkaboutdesign · 2026-08-24