{
  "id": 2879906,
  "title": "We Taught a 230M Language Model to Keep Learning on Android",
  "url": "https://urgent.news/2026/08/23/we-taught-a-230m-language-model-to-keep-learning-on-android",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-23T21:55:22.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/ijulin/we-taught-a-230m-language-model-to-keep-learning-on-android-36hl"
  },
  "original_language": "en",
  "account": "We have developed an open-source prototype called Online-SDFT, which fine-tunes a small language model on Android devices using delayed interactions. This allows the model to learn and continuously improve based on real-world usage patterns, rather than being limited to predetermined actions. The prototype utilizes a rank-4 LoRA adapter, ONNX Runtime training, and an on-device replay buffer to store relevant information. By using soft targets and controlled exploration, Online-SDFT can make better decisions and adapt to the user's preferences over time. Our initial results on synthetic notification streams show that Online-SDFT outperforms other methods, achieving a preference accuracy of 70.3% compared to 28.2% for the frozen base model and 50.0% for RAG. The replay buffer plays a crucial role in this learning process, as its removal significantly impacts the model's performance.",
  "summary": "Small language models can now run directly on phones. But most of them stop learning the moment they ship. For personal AI, that feels like a strange stopping point. Some of the most useful signals arrive only after the model acts: Did the user dismiss the notification? Did they open it later? Did they rewrite the suggestion? Did they ask for it again? These interactions contain useful…",
  "key_points": [],
  "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."
}