{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreicaxugthdocl5iwvfwzzbzwknaap347ayzxak6jcmhnblpbcjsra4",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mmdr5syneof2"
},
"path": "/t/intermittent-multiple-responses-in-single-output-with-gpt-5-2-chat-latest/1369727#post_3",
"publishedAt": "2026-05-21T05:08:28.000Z",
"site": "https://community.openai.com",
"tags": [
"Regression: Double responses in apps"
],
"textContent": "Cross-linking — same behavior on **gpt-5.5 (thinking)** at the raw API level (Responses API), still present months later. A cross-model A/B isolates it to gpt-5.5 (gpt-4.1 0/30, claude-sonnet-4-6 0/30), and token billing confirms the model itself generates the duplicate — clean openings bill ~77–93 output tokens, doubled ones ~130–258. Consolidated evidence: Regression: Double responses in apps\n\nHappy to share request IDs / a sanitized payload.",
"title": "Intermittent Multiple Responses in Single Output with gpt-5.2-chat-latest"
}