Astra can read and write weights to improve Qwen
Astra can read and write weights to improve Qwen
The research team proposed Weight-Space Programming, discovering that GPT-6 Astra can directly read and write neural network weights: with only 17,253 weights, it can determine which game the network is trained on, and from scratch, write a small game network that defeats PPO trained for 100 million steps without gradients or training.
Same story — featured version shown《MIT experiment: GPT-6 Astra directly modifies Qwen3.5 weights, mathematical ability improves by about 6 times》
Same story3 other outlets also reported this
- Hacker News · 300+··First·Reading now
Astra can read and write neural network weights and improve Qwen3.5-0.8B
- QbitAI··+7 h 36 min
MIT experiment: GPT-6 Astra directly modifies Qwen3.5 weights, mathematical ability improves by about 6 times
Adds:MATH-500 score improvement from 7.9% to 48.1%.
- ITHome · AI··+7 h 39 min
MIT CSAIL proposes weight space programming: GPT-6 Astra modifies Qwen3.5-0.8B's weights by about 0.016%, boosting MATH-500 score to 6 times
Adds:GSM8K score improvement from 13.8% to 67.1% and IFEval score improvement from 21.0% to 62.3%.
- Latent Space··+2 d
Latent Space reports on the latest trends in the AI field and in-depth interviews
In order of publication · later reports are added as they appear · Compared by AI from each outlet’s title and summary
Source: Hacker News · 300+ · rikiyat.github.io