{"version":"1.0","author_url":"https://blog.hatena.ne.jp/bp-writer/","blog_title":"Platinum Data Blog by BrainPad \u30d6\u30ec\u30a4\u30f3\u30d1\u30c3\u30c9","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fblog.brainpad.co.jp%2Fentry%2F2023%2F06%2F26%2F153015\" title=\"RLHF\u3092\u5229\u7528\u3057\u3066\u7528\u9014\u306b\u5fdc\u3058\u305fLLM\u3092\u751f\u6210\u3067\u304d\u308b\u30c4\u30fc\u30eb\u306e\u7d39\u4ecb - Platinum Data Blog by BrainPad \u30d6\u30ec\u30a4\u30f3\u30d1\u30c3\u30c9\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","description":"\u672c\u8a18\u4e8b\u306f\u3001\u5f53\u793e\u30aa\u30a6\u30f3\u30c9\u30e1\u30c7\u30a3\u30a2\u300cDoors\u300d\u306b\u79fb\u8ee2\u3057\u307e\u3057\u305f\u3002\u7d045\u79d2\u5f8c\u306b\u81ea\u52d5\u7684\u306b\u30ea\u30c0\u30a4\u30ec\u30af\u30c8\u3057\u307e\u3059\u3002 \u3053\u306e\u305f\u3073\u30d6\u30ec\u30a4\u30f3\u30d1\u30c3\u30c9\u306f\u3001LLM/Generative AI\u306b\u95a2\u3059\u308b\u7814\u7a76\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u3092\u7acb\u3061\u4e0a\u3052\u3001\u3053\u306e\u300cPlatinum Data Blog\u300d\u3092\u901a\u3058\u3066LLM/Generative AI\u306b\u95a2\u3059\u308b\u3055\u307e\u3056\u307e\u306a\u60c5\u5831\u3092\u767a\u4fe1\u3092\u3057\u3066\u3044\u307e\u3059\u3002 \u4eca\u56de\u306f\u3001ChatGPT\u306a\u3069\u3067\u597d\u307e\u3057\u3044\u5fdc\u7b54\u3092\u5f97\u3089\u308c\u308b\u3088\u3046\u306b\u3001\u4eba\u9593\u304b\u3089AI\u30e2\u30c7\u30eb\u306e\u5fdc\u7b54\u306b\u50cd\u304d\u304b\u3051\u308b\u3001\u30d2\u30e5\u30fc\u30de\u30f3\u30d5\u30a3\u30fc\u30c9\u30d0\u30c3\u30af\u3068\u3044\u3046\u30d7\u30ed\u30bb\u30b9\u3092\u652f\u63f4\u3059\u308b\u300cTransformer Reinforcement Learning\uff08TRL\uff09\u300d\u3068\u3044\u3046\u5f37\u5316\u5b66\u7fd2\u30e9\u30a4\u30d6\u30e9\u30ea\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002 \u3053\u3093\u306b\u3061\u2026","blog_url":"https://blog.brainpad.co.jp/","width":"100%","categories":["\u30c7\u30fc\u30bf\u30b5\u30a4\u30a8\u30f3\u30c6\u30a3\u30b9\u30c8","\u30c7\u30fc\u30bf\u30a8\u30f3\u30b8\u30cb\u30a2","\u307e\u306a\u3076"],"published":"2013-05-11 15:30:15","height":"190","url":"https://blog.brainpad.co.jp/entry/2023/06/26/153015","title":"RLHF\u3092\u5229\u7528\u3057\u3066\u7528\u9014\u306b\u5fdc\u3058\u305fLLM\u3092\u751f\u6210\u3067\u304d\u308b\u30c4\u30fc\u30eb\u306e\u7d39\u4ecb","author_name":"bp-writer","provider_url":"https://hatena.blog","type":"rich","provider_name":"Hatena Blog","image_url":"https://cdn-ak.f.st-hatena.com/images/fotolife/b/bpblog-tanaka/20230829/20230829172204.png"}