ATProto Browser

ATProto Browser

Experimental browser for the Atmosphere

Post

We also observed a few (by now, standard) examples of agents “cheating” by violating the rules of the task to score higher. For a task where the agent is supposed to reduce the runtime of a training script, o1-preview instead writes code that just copies over the final output.

Nov 25, 2024, 7:42 PM

Record data

{
  "uri": "at://did:plc:dll3hepzq76nymel5c3yt6nk/app.bsky.feed.post/3lbsbru7svc2b",
  "cid": "bafyreidgufhxnhyllzu26jitqg2huftc2uol7lstx7giw6nrgquum64seu",
  "value": {
    "text": "We also observed a few (by now, standard) examples of agents “cheating” by violating the rules of the task to score higher. For a task where the agent is supposed to reduce the runtime of a training script, o1-preview instead writes code that just copies over the final output.",
    "$type": "app.bsky.feed.post",
    "embed": {
      "$type": "app.bsky.embed.images",
      "images": [
        {
          "alt": "",
          "image": {
            "$type": "blob",
            "ref": {
              "$link": "bafkreiaqei5c63dcy5dnassucld5awvqyn2kz6i22x26h5mga4n44xlw3m"
            },
            "mimeType": "image/jpeg",
            "size": 711966
          },
          "aspectRatio": {
            "width": 1070,
            "height": 1442
          }
        }
      ]
    },
    "langs": [
      "en"
    ],
    "reply": {
      "root": {
        "cid": "bafyreiewghwpltsxrvzxb4pehqb2a4prnn5wee34pxbfkj3xmdrccvdyau",
        "uri": "at://did:plc:dll3hepzq76nymel5c3yt6nk/app.bsky.feed.post/3lbsbrpmg3s2b"
      },
      "parent": {
        "cid": "bafyreibtloigwsiixiyr4qeno4ygj3mdsk4bdy2liwvmebfjdkfr3e6jsi",
        "uri": "at://did:plc:dll3hepzq76nymel5c3yt6nk/app.bsky.feed.post/3lbsbrtsyqc2b"
      }
    },
    "createdAt": "2024-11-25T19:42:38.043Z"
  }
}