なぜ私の要約に「月曜日」のダイアログが表示されるのですか?

「月曜日」の会話が要約に表示されるのですが:

ログでこれを確認しました。モデルがフォーマットを解釈するのに役立つことを意図しているようですが、ユーザーには表示されるべきではありません。

この動作は、次の 2 つのことを変更した後に始まりました。

  1. sonnet 3.5 から haiku 3.5 に切り替えました。
  2. AiSummary.destroy_all を使用して ai_summaries テーブルの既存の要約を削除しました。これは十分ではないのかもしれませんか?

Claude Haiku 3.5に変更した後、すべての要約がこのようになりますか?

「いいね!」 1

いいえ、約半分、生成された要約10個のうち約5個です。sonnetに戻して修正されるか試しましたが、レート制限に引っかかっているので、これを特徴付けるには時間がかかるかもしれません。

これが発生したトピックのAPIリクエストとレスポンス全体を確認し、共有していただけますか? ai_api_audit_logs テーブルにあります。

「いいね!」 2

残念ながら、現時点ではありません。しかし、以前にそのトピックを調べたところ、月曜日については言及されておらず、有効な要約であることがわかりました。応答後に混乱する可能性はありますか?何も思いつかなければ、数日中に、より明確な例を挙げます。

「いいね!」 1

ai_api_audit_logs へのロギングは保証されており、成功した応答はすべてそこに記録されるため、プロンプト全体が表示されるはずです。データエクスプローラーを実行してテーブルの内容を確認することは可能ですか?

「いいね!」 1

月曜日になると、少なくとも haiku では Anthropic のレート制限に達してしまいます。レート制限を修正しようとすることはできますが、エラーが発生して月曜日が表示されないようにしたいです。

/logs:

Job exception: {"type":"error","error":{"type":"rate_limit_error","message":"Number of request tokens has exceeded your per-minute rate limit (https://docs.anthropic.com/en/api/rate-limits); see the response headers for current usage. Please reduce the prompt length or the maximum tokens requested, or try again later. You may also contact sales at https://www.anthropic.com/contact-sales to discuss your options for a rate limit increase."}}

ai_api_audit_logs からのリクエスト。実際のユーザーコンテンツは編集済みです。

{
  "model": "claude-3-haiku-20240307",
  "max_tokens": 3000,
  "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": "Two users are sharing their feelings toward Mondays. [user1](/t/-/11772/1) hates them, while [user2](/t/-/11772/2) loves them."
    },
    {
      "role": "user",
      "content": "he discussion title is: [redacted].\n\nHere are the posts, inside <input>[redacted]</input> XML tags:\n\n<input></input>\n\nGenerate a concise, coherent summary of the text above maintaining the original language."
    }
  ],
  "system": "You are an advanced summarization bot that generates concise, coherent summaries of provided text.\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 [NAME](/t/-/11772/POST_NUMBER)\n  - Example: link to the 3rd post by sam: [sam](/t/-/11772/3)\n  - Example: link to the 6th post by jane: [agreed with](/t/-/11772/6)\n  - Example: link to the 13th post by joe: [#13](/t/-/11772/13)\n- When formatting usernames either use @USERNMAE OR [USERNAME](/t/-/11772/POST_NUMBER)"
}

ai_api_audit_logs からの応答:

{
  "id": "msg_01QPVSmg93tu21WtPUvoNZ33",
  "type": "message",
  "role": "assistant",
  "model": "claude-3-haiku-20240307",
  "content": [
    {
      "type": "text",
      "text": "Summary:\n\nTwo users are sharing their feelings toward Mondays. [user1](/t/-/11772/1) loves them, while [user2](/t/-/11772/2) hates them."
    }
  ],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 7298,
    "output_tokens": 49
  }
}

要約ボタンをクリックすると、これが表示されます。

それは、レート制限に達したときに429ではなく200の応答を返していることを意味します。

これは彼らのAPIのバグになります。そこにバグレポートを開いてもらえますか?

「いいね!」 1

ヘッダーを含むネットワークトラフィックが必要とのことです。ブラウザで「要約」ボタンを押しても、サイドキックジョブをトリガーしても、それを取得する方法がわかりません。

それをログに記録しません。サーバーからcURLを発行し、それを転送する必要があります。

「いいね!」 1

また、msg_01QPVSmg93tu21WtPUvoNZ33 を提供することもできます。これにより、ログで直接検索できます。

「いいね!」 3

サム @markschmucker が提供したリクエストIDからAnthropicからのニュースはありますか?

まだレート制限がかかっている場合は、バックフィルバッチサイズを半分にすることを試してみてください。

「いいね!」 1

通常のサポートチケットシステムはなく、代わりにボットと話します。@samが提供したメッセージIDを含めて、ボットに問題を報告しました。ボットは納得し、人間への引き継ぎを約束し、新しいステータスがあればメールで通知すると約束しました。まだメールはありません。

「いいね!」 3

本日、Anthropicから「まだ起こっていますか?」というチャットメッセージを受け取りました。はい、まだ起こっています。それ以上のフィードバックはありませんでした。フラストレーションのたまる経験でした。

Anthropicからの返信:

こんにちは、

残念ながら、現時点ではこのエラーは再現されていません。

よろしく、
Ryan

これ以上進める方法がわかりません。cURLで独自のテストを作成することはできますが、Discourseが行っていることを正確に再現できるとは思えません。

Discourse は cURL と同じ HTTP 呼び出しを行うため、100% の忠実度で再現することが可能です。

とはいえ、Anthropic は増大する需要に対応するのに苦労していることがよく知られているため、AWS または Google Cloud 経由で Claude を使用するか、Gemini やその他の LLM API を試す方が簡単な場合があります。