Glitch in the Hallway: Benchmarking AI Spatial Logic Against Optical Illusions

Key Points

• The aim is to assess AI systems' spatial logic and visual reasoning capabilities through optical illusions.
• Conducted a visual reasoning probe comparing different AI models.
• Focused on transparency-related inference tasks.
• Utilized optical illusions as the primary evaluation tool.
• Identified performance variations among AI systems in spatial reasoning tasks.
• Noted specific strengths and weaknesses in handling optical illusions.