ATProto Browser

Record data

{
  "uri": "at://did:plc:x2a3inabvfsn4wntrlbbndrv/app.bsky.feed.post/3llet5qyih22c",
  "cid": "bafyreiajq5psz6xmuw2xbnjhjheii5nepctkj6b6c6a2bvh67keqswejiu",
  "value": {
    "text": "The basic idea premise behind language model reinforcement learning techniques is that by iteratively generating new proposals and refining them with verifiable feedback/rewards (e.g., from a formal proof checker), the language model can eventually discover useful behaviors and capabilities.\n\n2/",
    "$type": "app.bsky.feed.post",
    "embed": {
      "$type": "app.bsky.embed.images",
      "images": [
        {
          "alt": "",
          "image": {
            "$type": "blob",
            "ref": {
              "$link": "bafkreidcrilmbj2pkkf64wah2a4xtipq7sq7bu5dsscaecuri3rbeb6wty"
            },
            "mimeType": "image/jpeg",
            "size": 299410
          },
          "aspectRatio": {
            "width": 1338,
            "height": 740
          }
        },
        {
          "alt": "",
          "image": {
            "$type": "blob",
            "ref": {
              "$link": "bafkreieyy6ptt6vihx2kne64rynnoget7k5rfoy62ncsidltfe33gftvym"
            },
            "mimeType": "image/jpeg",
            "size": 65226
          },
          "aspectRatio": {
            "width": 520,
            "height": 272
          }
        }
      ]
    },
    "langs": [
      "en"
    ],
    "reply": {
      "root": {
        "cid": "bafyreidzv7o2gllewwfqqi4ixremjopxmuyntc5gstydqektrxkcjni4pi",
        "uri": "at://did:plc:x2a3inabvfsn4wntrlbbndrv/app.bsky.feed.post/3llet5p66ac2c"
      },
      "parent": {
        "cid": "bafyreidzv7o2gllewwfqqi4ixremjopxmuyntc5gstydqektrxkcjni4pi",
        "uri": "at://did:plc:x2a3inabvfsn4wntrlbbndrv/app.bsky.feed.post/3llet5p66ac2c"
      }
    },
    "createdAt": "2025-03-27T17:28:13.771Z"
  }
}