CDCK/MoM이 User1, User2 등으로 게시물을 인용 -- LLM 품질 문제?

Falco · 8월 10, 2026, 4:49오후

리포트 감사합니다. 이 PR에서 해당 문제를 처리합니다:

github.com/discourse/discourse

DEV: Use a realistic few-shot example in the summarizer agent (#42445)

main ← dev-summarizer-realistic-example

merged 06:41PM - 07 Aug 26 UTC

xfalcox

+14 -3

Previously, the summarizer agent's few-shot example used a two-post toy thread w…hose format didn't match the prompts the summarization strategies actually build, and the system prompt described a post format (`N) username message`) that no strategy emits. This change replaces the example with one mirroring a real captured request (discussion title line, posts inside `<input></input>` tags in the real `(N username said: ...` format) paired with a multi-paragraph cited summary demonstrating `[username]({resource_url}/N)` citations, and fixes the post format description to match what the topic, chat, and gist strategies actually send.

해당 토픽의 요약이 이제 더 좋아 보입니다.

글		댓글	조회수
Moderation tool for formatting code with AI Feature ai	10	372	4월 3, 2025
Code fences don't seem to deal with C comments Support	26	4739	10월 6, 2015
HTML comments are also summarized by AI Feature ai , ai-summarize	5	259	7월 1, 2026
Pasted content gains erroneous line breaks Bug needs-repro	5	222	8월 19, 2024
Catch and educate users posting code without properly formatting it Feature	28	5470	4월 11, 2019

CDCK/MoM이 User1, User2 등으로 게시물을 인용 -- LLM 품질 문제?

Related topics