Fable and Gemini Vision Models Misled by Place Names in Geo-Guessing Fail
HanchungLee · x · 2026-08-04
A developer noted that a show titled 'Cupertino' used an aerial photo not actually taken in the city. Both Fable 5 and Gemini Spark models failed hard in identifying the location.
The models were misled by the word 'Cupertino' in the prompt, confidently claiming it was Main Street Cupertino. The author pointed out this is factually incorrect, as a real Cupertino aerial would prominently feature Apple buildings, Asian grocery stores, and boba shops.
Related event: Multimodal LLMs Struggle with Geo-Guessing Tasks(2 posts)→
More from Fun
- Programming Robots With the Wrong Lab Music Shows — broodsugar · 2026-08-04
- From GANs to Agent Swarms: An AI Vet Reencounters 'Adversarial Collapse' 12 Years Later — bingxu_ · 2026-08-04
- US Frontier Labs Tout 'Efficiency' as Chinese Models Drop at Throwaway Prices — deliprao · 2026-08-04
- AI-generated funny image: robot slips on banana peel, netizens find it hilarious — Rare_Bunch4348 · 2026-08-04
- Omni Model Generates Complex Animations from a Single Prompt — jnack · 2026-08-04
- Dream Fulfilled: User Transforms into a Mexican Cyclops Using Generative AI — Quirky_Spirit_1951 · 2026-08-04