{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreib5q6nu2xlhir2n7o3gccrh65gkdny75y5mbojt2qtxmqbymsyzpm",
    "uri": "at://did:plc:tc32tkde4ezyincaupswyzc6/app.bsky.feed.post/3mfts5v3crow2"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreiblq3wqbt5gewbqpvfd2dcif7lthr4xh6bn4ijrioze7qdcyvadm4"
    },
    "mimeType": "image/png",
    "size": 3910
  },
  "path": "/incidents/1xs8w0shdkh2",
  "publishedAt": "2026-02-26T22:23:32.000Z",
  "site": "https://status.digitalocean.com",
  "textContent": "Feb 26, 22:23 UTC\n**Resolved** - Issue resolved.\nCause: A few requests made to the Llama 3.3-70B model caused issues.\nImpact: Intermittent errors when interacting with the model through serverless inference and/or with agents created using this model.\nContact support if issues persist.\n\nFeb 26, 21:52 UTC\n**Monitoring** - Fix deployed. Monitoring resources related to the Llama 3.3-70B.\nUsers should no longer experience intermittent errors when making serverless inference requests via APIs and Agents . Awaiting confirmation before closure.\n\nFeb 26, 16:00 UTC\n**Investigating** - We are currently investigating an issue affecting the Llama 3.3-70B model.\nSymptoms: Users may encounter intermittent errors when making serverless inference requests via APIs and Agents.\nCurrent Status: Our engineering team is actively investigating the issue to determine the root cause.",
  "title": "Intermittent Errors with Llama 3.3-70B",
  "updatedAt": "2026-02-26T22:23:32.000Z"
}