AnalysisOpinion / analysisEvaluation & Benchmarks · Multimodal Models · Reasoning & Planning1 source · Oct 12, 2026

Import AI 476: Creativity and RSI; worse-than-China open weight models; AI goes to space

New benchmark shows how AI models lack intuitive visual reasoning:

Proof1 independent outlet

Import AI runs on arXiv, cappuccinos, and feedback from readers.
...Humanity’s Sixth Sense highlights some shortcomings of current AI systems...
Why this matters - HSS tells us whether world models are emergent: One way of looking at HSS is highlighting deficiencies in current systems, but a more interesting way is highlighting how adept today’s frontier LLMs are at doing tasks which many people have long assumed would require sophisticated, different AI systems to solve.
Read the paper here: Humanity’s Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models (Scale Labs).

[1]Import AI 476: Creativity and RSI; worse-than-China open weight models; AI goes to space
Import AI (Jack Clark) · Oct 12, 12:30 PM
New benchmark shows how AI models lack intuitive visual reasoning:
Import AI runs on arXiv, cappuccinos, and feedback from readers.

Extractive summary: sentences quoted from the sources.

Before this