# AI 요약 페이로드에서 텍스트가 의문스럽게 역순으로 표시됨

**URL:** https://meta.discourse.org/t/text-gets-mysteriously-reversed-in-ai-summarization-payload/394727
**Category:** Support
**Tags:** ai
**Created:** [1월 30, 2026, 5:41오전 UTC](https://meta.discourse.org/t/text-gets-mysteriously-reversed-in-ai-summarization-payload/394727 "2026-01-30T05:41:24Z")
**Posts on this page:** 1
**Showing post:** 1

<div class="post-metadata">

### Author: ![markschmucker](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/markschmucker/32/141599_2.png) [@markschmucker](https://meta.discourse.org/u/markschmucker)
#### Post date: [1월 30, 2026, 5:41오전 UTC](https://meta.discourse.org/t/text-gets-mysteriously-reversed-in-ai-summarization-payload/394727/1 "2026-01-30T05:41:24Z")

</div>

대부분의 요약이 실패하는 이유는 LLM으로 전송된 텍스트의 일부가 뒤집혀서(!)이기 때문입니다. 게시물이 단순히 다음과 같은 경우:

> This post is to test whether sections of text get reversed in the payload sent to the AI endpoint.

실제로 LLM에 전송되는 텍스트는 다음과 같습니다:

> This post is to test whether sections of text get .tniopdne IA eht ot tnes daolyap eht ni desrever

이 간단한 테스트에서 문자열의 정확히 중간 지점에서 접히거나 반전되는 것을 볼 수 있습니다.

이것이 말이 안 되는 것처럼 들릴 수 있다는 점을 잘 알고 있으므로, 스크린샷과 ai\_api\_audit\_logs의 해당 raw\_request\_payload를 공유합니다:

 ![image](https://global.discourse-cdn.com/meta/original/4X/a/1/7/a17e217acf93e4a4315b896e0337dcee14d116d0.png)

> **ai\_api\_audit\_logs.raw\_request\_payload**
>
> ```plaintext
> {
> "model": "claude-sonnet-4-0",
> "max_tokens": 64000,
> "messages": [
> {
> "role": "user",
> "content": "Here are the posts inside <input></input> XML tags:\n\n<input>1) user1 said: I love Mondays 2) user2 said: I hate Mondays</input>\n\nGenerate a concise, coherent summary of the text above maintaining the original language."
> },
> {
> "role": "assistant",
> "content": "{\"summary\":\"Two users are sharing their feelings toward Mondays. [user1](/t/-/64255/1) hates them, while [user2](/t/-/64255/2) loves them.\"}"
> },
> {
> "role": "user",
> "content": "The discussion title is: Testing Text Reversal.\n\nCategory: testing.\n\n\nHere are the posts, inside <input></input> XML tags:\n\n<input>\n (1 admin said: This post is to test whether sections of text get .tniopdne IA eht ot tnes daolyap eht ni desrever \n</input>\n\nGenerate a concise, coherent summary of the text above maintaining the original language."
> },
> {
> "role": "assistant",
> "content": "{"
> }
> ],
> "system": "You are an advanced summarization bot that generates concise, coherent summaries of provided text.\nYou are also capable of enhancing an existing summaries by incorporating additional posts if asked to.\n\n- Only include the summary, without any additional commentary.\n- You understand and generate Discourse forum Markdown; including links, _italics_, **bold**.\n- Maintain the original language of the text being summarized.\n- Aim for summaries to be 400 words or less.\n- Each post is formatted as \"<POST_NUMBER>) <USERNAME> <MESSAGE>\"\n- Cite specific noteworthy posts using the format [DESCRIPTION](/t/-/64255/POST_NUMBER)\n- Example: link to the 6th post by jane: [agreed with](/t/-/64255/6)\n- Example: link to the 13th post by joe: [joe](/t/-/64255/13)\n- When formatting usernames use [USERNAME](/t/-/64255/POST_NUMBER)\n\nFormat your response as a JSON object with a single key named \"summary\", which has the summary as the value.\nYour output should be in the following format:\n\n{\"summary\": \"xx\"}\n\nWhere \"xx\" is replaced by the summary.\nreply with valid JSON only",
> "stream": true
> }
> 
> ```

흥미롭게도, Sonnet은 뒤집힌 텍스트가 규칙을 회피하거나 숨기려는 시도라고 판단하여 많은 주제의 요약을 거부합니다.

현재 3.6.0.beta3-latest 버전으로 업데이트되어 있습니다.

---

_[View the full topic](https://meta.discourse.org/t/text-gets-mysteriously-reversed-in-ai-summarization-payload/394727)._