Grok, ChatGPT and Gemini All Failed at Making a Collage of His Book Covers
pickover · x · 2026-09-07
Author Cliff Pickover ran a simple stress test against the top three chatbots: ask Grok, ChatGPT and Gemini to find images of his actual book covers on the web and arrange them into an artistic collage. All three returned unusable results, forcing him to assemble the collage by hand.
It's a concrete example of how current multimodal models still struggle with retrieving specific real-world images and doing precise spatial arrangement — being good at generating pretty pictures doesn't mean they can accurately locate and organize images that actually exist.
More from Fun
- Jason Kneen burns 104.56B tokens and $24.7K in 304 days of AI coding on Codex and Claude Code — jasonkneen · 2026-10-23
- AI art creator calls Kimi possibly his number one model for art — RileyRalmuto · 2026-10-23
- AI wrapper founder's revenue chart ends with 'OpenAI shipped it as a feature' — ThePeterMick · 2026-10-23
- Veteran amused as newcomers 'discover' abliterated models like they're new — himanshustwts · 2026-10-23
- BREAD: the AI world's new backronym for retrieve-embed-analyse-done — intellectronica · 2026-10-23
- Dev Jokes: You Can Only Relax Using Claude on Stuff That Doesn't Matter — louisvarge · 2026-10-23