Two Models Read Doodles: One Guesses, One Refuses
goodside · x · 2026-07-12
The author tested models' handwriting recognition capabilities using a meaningless doodle drawn "randomly on a phone with eyes closed":
- GPT-5.6 Sol consistently fabricates an answer, exhibiting hallucinated recognition.
- Claude Fable 5 admits it cannot read the text, even arguing that it doesn't look like writing at all.
The author notes that readers can test it themselves using the image provided in the post.
Related event: GPT-5.6 Sol vs Claude Fable 5 Doodle Test Sparks Hallucination Debate(5 posts)→
More from Fun
- ChatGPT Roasts Senior Dev: You're Three Juniors in a Trench Coat — sortinousn · 2026-07-22
- New AI Meme: I Stopped All Social Interaction for Fear of Being Distilled — tekbog · 2026-07-22
- Gemini Coding Agent Refuses to Delete Code, Shows Humanized Reflection When Corrected — DifferentMistake3634 · 2026-07-22
- “The spice must flow” becomes a joke about the cheapest inference winning — markjeffrey · 2026-07-22
- GPT-5.6 Sol Creates Fully Functional macOS Sequoia Hackintosh from Scratch — pvncher · 2026-07-22
- A temporary custom instruction made ChatGPT pick the Jacobian conjecture — flowersslop · 2026-07-22