One riddle, very different answers: models tackle the frenemy of my frenemy
Miles_Brundage · x · 2026-11-15
Miles Brundage tested models with "The frenemy of my frenemy is my ?" ChatGPT answered with a punny "Frenemaybe. It's complicated." Another model used algebra: with friend=+1 and enemy=−1, a frenemy is an even mix, and the product stays the same mix; model it as i and the frenemy of your frenemy becomes your enemy—four frenemies make a friend. Gemini 4 Carbon gave a similar algebraic take with personality metaphors. Brundage quips that only ChatGPT was annoying here, unexpected for an instant-tier model.
Related event: Frenemy fill-in-the-blank test exposes wildly different LLM answers(2 posts)→
More from Fun
- Will Depue's Blackwell 'forensic evidence' claim on DeepSeek hits snag: V4.1-Flash not cracked — teortaxesTex · 2026-11-15
- Want to run 'Opus 5.5' locally? This photo shows what it actually takes — demian_ai · 2026-11-15
- Comic nails it: your 'pure Python' is mostly C wearing a Python hat — lemire · 2026-11-15
- "I'm ESL so I can't write without AI" sparks debate in AI circles — TuhinChakr · 2026-11-15
- Musk posts then-and-now: Falcon 1 debris to Starship stacked on the tower — beffjezos · 2026-11-15
- Maker meme goes viral: grandfather eyeballs parts to micrometer tolerance — haydendevs · 2026-11-15