{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreihzsk2udnghnycv6gnbfegewycw2dqk6gmq7z6mns4jwmkgl7oljy",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mfuyzhriwpa2"
  },
  "path": "/t/fine-tuned-4o-errors-using-the-responses-api-with-image-input/1375316#post_2",
  "publishedAt": "2026-02-28T00:24:02.000Z",
  "site": "https://community.openai.com",
  "textContent": "Yep, Situation abnormal, same long-persisting system as happened weeks ago for weeks.\n\nAt `top_p:0`\n\n  * no response for minutes\n  * a response that has vision based text\n  * a constant loop of “assistant”\n\n\n\nalso: complete random inconsistent responses when the model does respond - top_p:0 not working at all to normalize the output. Have to go with temp and top p: 0.01. To get the same amount of assistant message spam until max_output_tokens.\n\n",
  "title": "Fine-tuned 4o errors using the responses API (with image input)"
}