An AI Rewrote Another Model’s Weights: Math Score 8% to 48%
MIT researchers let GPT-6 Astra edit 0.016% of a small model’s weights, no training. Its math score jumped from 7.9% to 48.1%.
MIT researchers let GPT-6 Astra edit 0.016% of a small model’s weights, no training. Its math score jumped from 7.9% to 48.1%.
We use cookies to improve your experience, analyze traffic and for marketing. You can accept all cookies or choose which categories to allow.