{
  "id": 6354996,
  "title": "How LLMs Learned to Reason: SFT --> RLHF --> RLVR",
  "url": "https://urgent.news/2026/09/09/how-llms-learned-to-reason-sft-rlhf-rlvr",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-09T00:09:45.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/cyprus09/how-llms-learned-to-reason-sft-rlhf-rlvr-1ldh"
  },
  "original_language": "en",
  "account": "The Last Non-Reasoning Flagships GPT-4.5, DeepSeek-V3, and Claude 3.5 Sonnet were the final major models constructed using the pretrain, then instruct-tune recipe. These models proceeded without any backtracking, verification, or revision mechanisms. As data and compute scaling reached a plateau, the focus shifted from larger models to a different training paradigm: training models to think before they answer.",
  "summary": "1. The Starting Line: The Last Non-Reasoning Flagships GPT-4.5, DeepSeek-V3, and Claude 3.5 Sonnet share something that has nothing to do with benchmark scores: they were the last major models built entirely on the \"pretrain, then instruct-tune\" recipe. All internal computation was done in one forward pass per token, with no backtracking, verification or revision mechanisms in place. By late…",
  "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."
}