ATProto Browser

ATProto Browser

Experimental browser for the Atmosphere

Post

The tasks in RE-Bench aim to cover a wide variety of skills required for AI R&D and enable apples-to-apples comparisons between humans and AI agents, while also being feasible for human experts given ≤8 hours and reasonable amounts of compute.

Nov 25, 2024, 7:42 PM

Record data

{
  "uri": "at://did:plc:dll3hepzq76nymel5c3yt6nk/app.bsky.feed.post/3lbsbrrjfbc2b",
  "cid": "bafyreie4xnq36ka4jnux2poaxzs6aoivtxyam7nkzzztfccscskjvuagwa",
  "value": {
    "text": "The tasks in RE-Bench aim to cover a wide variety of skills required for AI R&D and enable apples-to-apples comparisons between humans and AI agents, while also being feasible for human experts given ≤8 hours and reasonable amounts of compute.",
    "$type": "app.bsky.feed.post",
    "embed": {
      "$type": "app.bsky.embed.images",
      "images": [
        {
          "alt": "",
          "image": {
            "$type": "blob",
            "ref": {
              "$link": "bafkreifg55th2es6okxfgfwrnaplqlsgs6alvbnri3oba6kn2xjl25lksi"
            },
            "mimeType": "image/jpeg",
            "size": 476366
          },
          "aspectRatio": {
            "width": 1164,
            "height": 1202
          }
        }
      ]
    },
    "langs": [
      "en"
    ],
    "reply": {
      "root": {
        "cid": "bafyreiewghwpltsxrvzxb4pehqb2a4prnn5wee34pxbfkj3xmdrccvdyau",
        "uri": "at://did:plc:dll3hepzq76nymel5c3yt6nk/app.bsky.feed.post/3lbsbrpmg3s2b"
      },
      "parent": {
        "cid": "bafyreic5uu5vf57bfigz2g2cfrsfico5wy6acycwt2iu7bkj3v6okju5ta",
        "uri": "at://did:plc:dll3hepzq76nymel5c3yt6nk/app.bsky.feed.post/3lbsbrq52d22b"
      }
    },
    "createdAt": "2024-11-25T19:42:38.036Z"
  }
}