{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreihwqhx5dijx36g6smzjl42uukugjno7d5cy32e4i47ujprt5hofsq",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mlj2l36wzfa2"
  },
  "path": "/t/collection-of-gpt-image-generator-2-0-issues-bugs-and-work-around-tips-check-first-post/1379535?page=14#post_270",
  "publishedAt": "2026-05-10T13:16:54.000Z",
  "site": "https://community.openai.com",
  "textContent": "_j:\n\n> natural language.\n\nJust to double check, natural language for me as in my native languages?\n\nLarisaHaster:\n\n> If you as the human can’t correctly describe for example, how a human is supposed to hold a pen correctly, how an earth should we expect that LLM/image generators are supposed to know that?\n\nAnd about describing in prompts, like my hand dilemma, any good tip/workaround for that? Because that’s where I fail royally.\n\n(My post more above in this thread where I mentioned a little)",
  "title": "Collection of GPT-image-generator 2.0 issues, bugs, and work-around tips (check first post)"
}