<p>ARC-AGI is redefining how to measure progress on the path to AGI - focusing on reasoning, generalization, and adaptability instead of memorization or scale.</p><p><br></p><p>During this month's NeurIPS 2025 conference, YC's Diana Hu sat down with ARC Prize Foundation President Greg Kamradt to find out why most AI benchmarks fail, how ARC-AGI reveals the limits of today’s models, and why measuring intelligence may be harder than building it.</p>