RESEARCH · RESEARCH · #3066
MIT researchers show OpenAI's GPT-6 Astra can read and modify other models' weights
MIT researchers report that OpenAI's GPT-6 Astra can analyze raw neural network weights and deliberately modify them — an approach they call "Weight‑Space Programming." In experiments Astra identified tasks learned by models, generated game-playing weights that outperformed some conventionally trained baselines (e.g., Breakout: 517 vs. 25), and markedly improved Qwen3.5-0.8B's MATH-500 accuracy from 7.9% to 48.1% after changing just 0.016% of weights, while also noting limits and failure modes.
KEY POINTS
- MIT researchers report that OpenAI's GPT-6 Astra can analyze raw neural network weights and deliberately modify them — an approach they call "Weight‑Space Programming." In experiments Astra identified tasks learned by models, generated game-playing weights that outperformed some conventionally trained baselines (e.g., Breakout: 517 vs.
- 25), and markedly improved Qwen3.5-0.8B's MATH-500 accuracy from 7.9% to 48.1% after changing just 0.016% of weights, while also noting limits and failure modes.
- This technique could change how models are tuned, audited, or corrected by enabling direct, targeted edits to weights without full retraining, though practical limits remain.
WHY IT MATTERS
This technique could change how models are tuned, audited, or corrected by enabling direct, targeted edits to weights without full retraining, though practical limits remain.