{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreiejpgbhlr2x4zvygh3uvat3f5yhz5ywkucoztqjfzb5zoyg3cavem",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mexzuq4gdll2"
},
"path": "/t/realtime-api-feedback-we-built-a-star-trek-medical-computer-on-the-realtime-api-it-works-30-of-the-time/1373790#post_2",
"publishedAt": "2026-02-16T11:00:44.000Z",
"site": "https://community.openai.com",
"textContent": "multitechvisions:\n\n> Beyond 10-15 minutes, extraction accuracy drops noticeably. More idle calls, missed data, less precise tool arguments. Medical encounters run 20-40 minutes routinely. This is a critical gap for any real-world clinical deploymen\n\nI feel your pain on this, having seen the experience grow worse as time progresses. There is only a 32K input token limit. Have you experimented with calling conversation.item.delete on old items? perhaps with a separate model flagging what can be deleted, and perhaps even introducing a consolidation of several items and deleting them? That is on my TODO list to tackle this problem",
"title": "[REALTIME API] - FEEDBACK - We Built a Star Trek Medical Computer on the Realtime API, It Works 30% of the Time"
}