Comparing How Two Models Interpret Doodles
goodside · x · 2026-07-12
The author fed a meaningless doodle—literally just random scribbling with eyes closed on a phone screen—into GPT-5.6 Sol and Claude Fable 5. The results:
- Sol tends to confidently fabricate an answer, displaying hallucination tendencies.
- Fable directly admits it cannot read the text and even points out that it doesn't look like writing at all.
This is a classic showcase of how differently models react to ambiguous inputs.
Related event: GPT-5.6 Sol vs Claude Fable 5 Doodle Test Sparks Hallucination Debate(5 posts)→
More from Fun
- Cloudflare and Vercel’s public feud turns into a meme-level post — tekbog · 2026-07-22
- Tesla’s new Caraoke scoring update becomes a relationship joke — XFreeze · 2026-07-22
- Gemini Omni Flash turns a boat cabin into a cave in Flow by Google — chrisfirst · 2026-07-22
- GitHub review bot hits its PR limit and forces a 39-minute cooldown — DanielLockyer · 2026-07-22
- AI turns a revenge prompt into a self-help pep talk in a new meme screenshot — colorlys7 · 2026-07-22
- Hand-painted figurines run through Seedance look eerily alive — cocktailpeanut · 2026-07-22