AIHacker Newsabout 7 hours ago
Are AI Labs Pelicanmaxxing?
1 min read
Simon Willison's informal AI benchmark asks models to generate an SVG of a pelican riding a bicycle. An experiment tested 1,008 SVGs across seven frontier models including GPT-5.6 Terra, Claude Sonnet 5, and Gemini 3.5 Flash. Statistical analysis found no evidence that AI labs trained specifically on this benchmark, with pelicans ranking 6th out of 8 animals and bicycles second-to-last among vehicles.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
