{
  "id": 6634353,
  "title": "You Thought Training an AI Model Was Enough. Then There's Post-Training",
  "url": "https://urgent.news/2026/09/10/you-thought-training-an-ai-model-was-enough-then-theres-post-training",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-10T20:07:43.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/rijultp/you-thought-training-an-ai-model-was-enough-then-theres-post-training-e13"
  },
  "original_language": "en",
  "account": "Rijul is developing LiveReview, an AI code review system designed to assess the potential impact of code changes on business-critical systems. Training an AI model to become a helpful assistant involves more than just feeding it large amounts of data. Post-training techniques are necessary to ensure the model responds appropriately to questions and follows instructions.\n\nSupervised Fine-Tuning (SFT) is one such technique where the model is shown thousands of example responses crafted by humans or strong existing models. The goal is to teach the model to produce the expected format, follow instructions, and respond helpfully. However, this method can be limited by the quality of the provided responses, especially when dealing with a vast number of potential questions.\n\nAn alternative approach is Direct Preference Optimization (DPO) and Proximal Policy Optimization (PPO). Both techniques rely on teaching the model to prefer certain responses over others. In DPO, the model is directly tuned using preference data, whereas PPO uses a separate reward model to predict the quality of responses before optimizing the language model. DPO is often easier to implement and can be more cost-effective than PPO, as it eliminates the need for a separate reward model during the preference optimization process.",
  "summary": "Hello, I'm Rijul, and I'm building LiveReview — a blast-radius aware AI code review built for your business-critical systems. Star us to help devs discover the project, give it a try, and share your feedback to help improve the product. When you think of AI models being trained, it's not merely about having a large set of data and training the model on it. When you are putting the model as the…",
  "key_points": [
    "Post-training techniques essential for AI model's helpfulness",
    "Supervised Fine-Tuning teaches model response format and instructions",
    "Direct Preference Optimization and Proximal Policy Optimization optimize response preference"
  ],
  "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."
}