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
- Five Years Into the AI Boom, Google Docs Still Red-Underlines 'Compute' as a Noun — ohlennart · 2026-09-11
- Open ECDSA.fail challenge uses AI agents to shrink Shor's-algorithm quantum circuits for Bitcoin keys — StefanoGogioso · 2026-09-11
- DHH Slams 'GDPR Is Good' Take: Vague Rules Birthed a Bureaucratic Beast — dhh · 2026-09-11
- Someone built a website where you can sign up for AI not to kill you — motionbynick · 2026-09-11
- Fruit fly brain as an LLM: connectome-driven language model demo goes live — ngxson · 2026-09-11
- Meme: Engineers Unleash 10,000 Claude Sub-Agents on Friday Afternoon to Clear a Week's Work — _jaydeepkarale · 2026-09-11