{
  "id": 17935937,
  "title": "Forget retraining - AI can now tweak another AI's weights",
  "url": "https://urgent.news/2026/11/03/forget-retraining-ai-can-now-tweak-another-ais-weights",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-03T08:15:00.000Z",
  "source": {
    "name": "The Register Science",
    "slug": "the-register-science",
    "url": "https://www.theregister.com/ai-and-ml/2026/11/03/forget-retraining-ai-can-now-tweak-another-ais-weights/5307105"
  },
  "original_language": "en",
  "account": "Recent research by MIT's CSAIL has shown that frontier AI models like OpenAI's GPT-6 Astra can directly edit the weights of another model, rather than just indirectly improving through training. This process, dubbed \"Weight-Space Programming,\" allows Astra to change as few as 0.016 percent of Qwen3.5-0.8B's weights, significantly improving its math abilities. The researchers found that Astra could program the neural network weights of a policy network from scratch, capable of playing Breakout as well as possible. This technique could improve model optimization, reduce catastrophic forgetting, and aid in model interpretability and alignment. The next step involves creating a benchmark for Weight-Space Programming to standardize and accelerate progress in this area.",
  "summary": "'Weight-Space Programming' fiddles with nerd knobs to boost benchmark scores",
  "key_points": [
    "MIT CSAIL researchers develop Weight-Space Programming",
    "Astra AI model edits 0.016% of Qwen3.5-0.8B weights",
    "Improves math abilities, aids model optimization"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}