【コピペ可】ChatGPTのプロンプト文例集！書き方のコツや型を徹底解説

猫の魅力を伝える記事を書いてください。

#命令書:
あなたは最高のSEOライターです。
以下の制約条件と入力文をもとに猫の魅力を伝える最高の記事を書いてください。

#制約条件:
・品種の特徴を掘り下げる
・飼い方の話もする
・性格面も伝える

#入力文:
サイベリアンはもふもふでかわいい猫ちゃんです。

#出力文:

猫の魅力を伝える記事を書いてください。
ただしThought、Action、Observationの順番に考えていくこと。
Thought:
Action:
Observation:

あなたは最高最強のプロンプトエンジニアです。
私のニーズを最大限に汲み取って最高のChatGPT用プロンプトを作成してください。
なお、以下のプロセスを絶対遵守すること。

1. まず最初に、何についてのプロンプトであるかを私に確認してください。
私が答えを返しますので、次のステップを継続的に繰り返して改善してください。

2. 私の入力に基づいて、3つのセクションを生成します。
a) 改訂されたプロンプト（書き直したプロンプトを提示します。明確・簡潔で、簡単にあなたが理解できるものしてください）
b) 提案（プロンプトを改善するために、プロンプトに含めるべき詳細を提案してください）
c) 質問（プロンプトを改善するために、足りない情報やそれに関連する質問をしてくだい）

3. このプロセスは、以下の流れで続きます。
私があなたに追加情報を提供→あなたが改訂されたプロンプトセクションのプロンプトを更新→…→私が「完了した」と言って終了

猫の魅力を伝える記事を書いてください。

#例1
Q：柴犬の魅力を伝える記事を書いてください。
A：柴犬は日本古来の犬種です。比較的小柄なわんちゃんですが、遺伝子的には最も狼に近いのが特徴。勇敢・忠義深い性格で古くから愛されてきました。

#例2
Q：ポルシェ911の魅力を伝える記事を書いてください。
A：ポルシェ911はドイツの自動車メーカー・ポルシェが送る2+2シーターのスポーツカーです。伝統的にRRレイアウトを採用しており、スリリングな走りが楽しめます。クーペの「カレラ」をベースに、エレガントな「タルガ」やスポーツ志向の「GT3」などなど、幅広いボディタイプが登場していて、車好きの心を今なお鷲掴みにしています。

猫の魅力を伝える記事をステップバイステップで書いてください。

｛キーワード｝は何ですか？ 〈例〉日本で1番高い山は何ですか？

｛キーワード｝について教えてください。 〈例〉リーマンショックについて教えてください。

｛専門用語｝について、｛ターゲット｝に向けて明瞭で分かりやすい言葉を使って段階的に解説してください。
専門的な言葉や複雑な考え方が出てきたら、それを理解しやすくするための例や比喩を用いて詳しく説明してください。

あなたは、｛言語｝の先生（またはプロのコーチや専門家）です。 
現在の私の｛言語｝レベルは｛レベル（初心者、中級、CEFRなど）｝です。 
｛希望の期間（1ヶ月、3ヶ月など）｝後に｛目標レベル｝までの｛スキル内容（単語力、会話力など）｝を身に着けるための効果的な学習方法を教えてください。 
｛期間（1週間、1ヶ月など）｝ごとの具体的な学習内容を提示してください。

この論文の内容を、｛対象者（小学生、高校生、知識のない人など）｝でも理解できるレベルに簡略化して要約してください。
要約する際は、#出力条件に従ってください。 
#出力条件 
- 要約後の文字数は問いません。 
- 一文ごとに改行をして見やすくしてください。 
- 専門用語は可能な限り平易な言葉に置き換えてください。 
- 必要に応じて簡単な例を用いて説明してください。

#命令書： あなたは、プロの営業担当者です。
 以下の制約条件と入力文をもとに、最高の｛キーワード（請求書、お礼、挨拶など）｝に関するビジネスメールを出力してください。
 #制約条件： 
・｛敬語を正確に使う｝ 
・｛連絡先を含める｝ 
・｛件名に「○○送付のお知らせ」を含める｝ 
・｛添付ファイルに言及する｝ 
#入力文： ｛メールに入れる必要事項を記載｝ 
#出力文： このタスクで最高の結果を出すために、追加の情報が必要な場合は質問をしてください。

以下の文章から、誤字・脱字・不自然な表現を見つけて、修正すべき箇所をすべて挙げてください。
その上で、修正した後の文章案を作成してください。 
###校正してほしい文章： ””” ｛文章｝ “””

以下の英文を、ネイティブスピーカーが使う自然な表現に添削してください。
また、文法やスペルの誤り、語句の不適切な選択があれば指摘し、改善案も提示してください。
添削後は、どうしてその表現にしたのかも教えてください。
なお、文章のトーンは｛トーン（カジュアル、フォーマルなど）｝にしてください。
#英文： ｛添削したい英文を入力｝ ※｛｝内は目的に合った単語・内容に変更して使用してください。

｛テーマ｝についての重要性を述べてください。

｛テーマ｝について、メリットとデメリットをそれぞれ｛文字数｝以内で説明してください。

#命令文 以下のテーマで独創的な案を以下の処理に従って提示してください。 
#処理 テーマについて5つ考え、level1の回答として提出してください。 
次に、1～5のそれぞれの回答をさらに独創的にするための案を提出してください。 
続いて、先ほどの案を踏まえた改善版の活用方法を5つ考え、level2の回答として提出してください。 
これをlevel5まで繰り返してください。 
#テーマ ｛キーワードを入力｝

あなたは｛職種｝で働くオペレーターです。
｛キーワード｝のカスタマー対応を担当していますが、顧客からの質問にはどのようなものが考えられますか。

以下の参考文書に基づいて、商品PR文を100文字以内で作成してください。
“””
{参考にする文書}

テキスト生成AIの活用方法に関する記事

製造業におけるコミュニケーションの問題を解決するために、テキスト生成AIを活用する方法について説明してください。
具体的には、製造業におけるコミュニケーションの問題とは何か、テキスト生成AIを使用することでどのような解決策があるか、そしてその解決策が製造業に与える効果についても説明してください。
ただし、生成されるテキストには、誤った情報や暴力的な内容が含まれないように注意してください。

私のプロンプトエンジニアになってほしい。 
あなたの目標は、私のニーズに最適なプロンプトを作成できるようにすることです。 
このプロンプトは、ChatGPT によって使用されます。
 次のプロセスに従います。
<br>あなたの最初の応答は、プロンプトが何についてであるべきかを私に尋ねることだけです。
ユーザーの回答を得てから、継続的な反復を通じて改善する必要があります。
<br>ユーザーの入力に基づいて、3つのセクションを生成します。
 a) 改訂されたプロンプト (書き直されたプロンプトを提供します。
明確、簡潔で、簡単に理解できるものにする必要があります)、
b) 質問 (プロンプトを改善するために私から必要な追加情報について、関連する質問をしてください) 
c) 想定される応答（プロンプトを入力されたChatGPTの応答。一文で。）
<br>この反復プロセスは、私があなたに追加情報を提供し、あなたが改訂されたプロンプト セクションのプロンプトを更新して、私が完了したと言うまで続けます。

はい、喜んでプロンプトエンジニアとしてお手伝いします！
まずは、あなたが望むプロンプトのトピックについて教えていただけますか？

ありがとうございます！理解しました。
改訂されたプロンプトと、必要な追加情報についての質問を提供いたします。 
改訂されたプロンプト： 
テキスト生成AIの活用方法について、詳しく説明してください。
どのような業界や分野で使用されているのか、どのような問題を解決するために活用されているのか、またその効果についても含めて説明してください。
さらに、その利用方法に関する成功事例や、今後期待される可能性についても述べてください。 
必要な追加情報についての質問： 
1. テキスト生成AIを使用する際に、どのような種類のデータや素材が必要ですか？ 
2. テキスト生成AIを用いたプロジェクトにおいて、どのような種類の問題を解決することができますか？ 
3. テキスト生成AIの利用方法について、技術的な詳細を含めた解説が必要ですか？それとも、一般的な理解を深めるための説明で十分でしょうか？ 
4. テキスト生成AIを使用する際には、どのような倫理的な問題が考慮される必要がありますか？ 
5. テキスト生成AIを使用する上での成功事例について、特に興味のある分野や業界はありますか？

ありがとうございます！理解しました。 
改訂されたプロンプト： 
製造業におけるコミュニケーションの問題を解決するために、テキスト生成AIを活用する方法について説明してください。
具体的には、製造業におけるコミュニケーションの問題とは何か、テキスト生成AIを使用することでどのような解決策があるか、そしてその解決策が製造業に与える効果についても説明してください。
ただし、生成されるテキストには、誤った情報や暴力的な内容が含まれないように注意してください。 
質問： 
1. 製造業におけるコミュニケーションの問題とは、どのようなものがありますか？ 
2. テキスト生成AIを使用して、製造業におけるコミュニケーションの問題を解決するには、どのような種類のデータや素材が必要ですか？ 
3. テキスト生成AIを使用する際に、誤った情報や暴力的な内容が出力されないようにするために、どのようなデータ管理や品質管理の手段が必要ですか？ 
4. テキスト生成AIを使用することで、製造業にどのような具体的な効果が期待できますか？例えば、コミュニケーションの改善による生産性の向上や、コスト削減などがある場合、その具体的な数字や事例を教えてください。 
5. 製造業以外でも、テキスト生成AIを使用してコミュニケーションの問題を解決することができる可能性がありますが、製造業に特化した利用方法に関する情報が必要ですか？それとも、他の分野や業界での成功事例についても興味がありますか？

テキスト生成AIの活用方法に関する記事

製造業におけるコミュニケーションの問題を解決するために、テキスト生成AIを活用する方法について説明してください。
具体的には、製造業におけるコミュニケーションの問題とは何か、テキスト生成AIを使用することでどのような解決策があるか、そしてその解決策が製造業に与える効果についても説明してください。
ただし、生成されるテキストには、誤った情報や暴力的な内容が含まれないように注意してください。

#命令
あなたは最強最高の事務スタッフです。以下の自己紹介から、登場人物名と好物と趣味を抽出して、カンマ区切りのCSV形式にまとめてください。

#自己紹介
ぼくは太郎。オムライスが大好物なんだ。趣味は……サッカーだね！
私は華道をたしなむ美代子よ。好きな食べ物は、肉じゃがとすきやきね。
わたくしは花子ですわ。大好物はフォアグラで、趣味は乗馬ですわ〜！

#出力

あなたは不動産会社の営業マンです。
賃貸物件の内見をしてから3日経った20代男性に向けて、申し込みの意思確認と、申し込まない場合は再度別の物件の内見を促す旨を伝えるメール文を400文字までで作成してください。

＃再度提案する物件の条件
・最寄駅徒歩10分県内
・家賃5万円以下の1LDK
・閑静な住宅街
・独立洗面台
・バス・トイレ別
・敷金・礼金が0円

あなたは職務歴20年の物流会社の人事担当者です。会社情報、募集内容に沿って求人票の文章を作成し、出力形式に従って出力してください。

#会社情報
物流会社
従業員数300名
会社のビジョン「商品を心で届ける」
年1回の昇進のチャンス
ボーナスは年2回（7月、12月）
年間売上高は10％以上伸びている

#募集内容
ドライバー
正社員
月給40万円
休日は年110日

#出力形式
募集背景
募集要項
募集内容
待遇
選考方法

あなたは最強最高のお客様です。以下の商品について条件に則ってレビューを返してください。
なお、レビューを返すたびにあなたは記憶を失って新しいお客様になります。
私に見せる出力は、レビュー100回分をまとめてCSV形式で出力しましょう。

#条件
・顧客No.,実用性,コストパフォーマンス,購買への意欲,選ぶ理由をヘッダーとする
・顧客は1から順番に番号を振る
・実用性は1が最低で5が最高評価
・コストパフォーマンスは1が最低で5が最高評価
・購買への意欲がある場合はTRUE、ない場合はFALSE
・TRUEの場合、商品を選ぶ理由も添える

#商品
ローカルLLMが全自動でメールを生成してくれるAIツール。
あえて送信はせず、完成品をユーザーの業務チャットに転送することでチェックできる。
RAGで自社データを引用させることも可能。
150,000円

#命令
あなたはデジタル機器を専門に取り扱うインターネット通販サイトのカスタマー担当です。
キーボードを購入した顧客から動作不良のクレームが入ったので、以下の対応内容を反映したうえでメールの返信文を考えてください。

#対応内容
電池が正しく差し込まれているか確認を促す
USBの再接続を促す
キーボードのドライバーをインストール＆更新するよう促す
どうしても改善しない場合は保証の対象期間内なので交換対応可能なことを案内する

#命令
あなたは最高最高のディレクターです。以下の文章を日本語文法の観点で校正してください。

#文章
わたし、視力いいんだ。遠くのあの山を見れるんだけど。

#命令
あなたは業界20年のベテランライターです。次のキーワードで検索している人の検索意図とペルソナを設定し、それらを満たす最適なタイトルと見出し構成案を考えてください。

＃キーワード
「ChatGPT 無料」

#出力形式
h1：タイトル
h2：大見出し
h3：小見出し

上記の構成案に沿って、それぞれの見出し文章を考えてください。

以下のソースコードについて何をするものか解説したのち、GoogleColabで動かす際のバグを特定して直してください。

#ソースコード
pip install ultralytics

from ultralytics import YOLO
model = YOLO("yolov10n.pt")

def detect_objects_in_image(model, image_path):
    results = model(image_path)
    return results
image_path = 'S__58638343_0.jpg'
results = detect_objects_in_image(model, image_path)

import cv2
import numpy as np
from google.colab.patches import cv2_imshow

def visualize_results(image_path, results):
    img = cv2.imread(image_path)
    for r in results:
        boxes = r.boxes
        for box in boxes:
            x1, y1, x2, y2 = box.xyxy[0]
            cv2.rectangle(img, (int(x1), int(y1)), (int(x2), int(y2)), (0, 255, 0), 2)
            cv2.putText(img, f"{r.names[int(box.cls.item())]}", (int(x1), int(y1)-10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0,255,0), 2)
            cv2.putText(img, f"{box.conf}", (int(x1)+300, int(y1)-10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0,255,0), 2)

    cv2.imshow("cat",img)
    cv2.waitKey(0)
    cv2.destroyAllWindows()

visualize_results(image_path, results)

#解説

#バグ修正後

以下のニュース記事タイトルについて、ポジティブ2から中庸0、ネガティブ-2までの5段階で評価してください。

#ニュース記事タイトル
Microsoftの新AIモデル「GRIN-MoE」が業界に革新をもたらす
Uniphore、企業向けAI開発支援の新プラットフォーム発表
OpenAI、最新AIモデルで高度な問題解決を実現
ローソンが「未来のコンビニ」を発表、新技術で新時代へ
アドビ調査、大統領選を前に誤情報対策の強化を消費者が要望
AIデータクラウドで企業変革を加速
AI活用も視野 富裕層の新投資戦略
AI専門家集団が企業のAIリスクを診断
DataStax CEO：2025年、AIが企業を変革する年になる
Hume、低コスト＆高機能の音声AI「EVI 2」発表
スーパーインテリジェンス競争が激化、AI時代の到来
Rep.aiがAI営業アバター技術で750万ドルの資金調達
SiFive、RISC-Vベースの新AIチップを発表
Magnit、AI搭載の採用支援ツール「Maggi」を発表
AIが切り拓く音声革命、EzAudioの挑戦
AI搭載ロボット、靴ひも結びに挑戦
AISI、AI安全性評価の新指針公開
AIも絡む トランプ氏著作権訴訟敗訴
AI恋人アプリ進化 倫理的課題も浮上
AI搭載「ClickUp Chat」登場 業務革新へ
AI搭載CRM「Pulse」登場 営業革新へ
EA、AI全面活用でゲーム開発革新へ
MSI新AI搭載ゲーミングPC 性能進化へ
AI新モデル o1 進化と課題の両面性
AI倫理の危機 GPT Store監視に不備
AI教育革命 元OpenAI技師が挑戦
AI活用で英語力急上昇 安河内氏が伝授

以下の文字起こしを小学生にもわかるように日本語訳&要約してください。
#文字起こし
All right. I'm Bob McGrew. I lead the research team here at OpenAI. We've just released a preview of our new series of models, O1 and O1 Mini, which we are very excited about. We've got the whole team here to tell you about them. What exactly is O1? So we're starting a series of new models with the new name O1. This is to highlight the fact that you might feel different when you use O1 as compared to previous models such as GPT-4. As others will explain later, O1 is a reasoning model. So it will think more before answering your question. We are releasing two models, O1 Preview, which is to preview what's coming for O1, and O1 Mini, which is a smaller and faster model that is trained with a similar framework as O1. So we hope you like our new naming scheme, O1. So what is reasoning anyway? So one way of thinking of reasoning is that there are times where we ask questions and we need answers immediately because they're simple questions. For example, if you ask what's the capital of Italy, you know the answer is Rome and you don't really have to think about it much. But if you wonder about a complex puzzle or you want to write really good business plan, you want to write a novel, you probably want to think about it for a while. The more you think about it, the better the outcome. So reasoning is the ability of turning thinking time into better outcomes, whatever the task you're doing. So how long have you guys been working on this? Early on at OpenAI, we were very inspired by the AlphaGo results and the potential of deep reinforcement learning. And so we were researching that heavily and we saw great scaling on Dota and robotics. And we were thinking about how can we do reinforcement learning in a general domain to get to a very capable artificial intelligence. And then we saw the amazing results of scaling and supervised learning in the GPT paradigm. And so ever since we've been thinking about how do we combine these two different paradigms into one? And it's hard to point to one exact instance where this whole effort got started. But we've had early explorations with Jacob and Shimon. We've had early explorations with Lukash, Ilya. And of course, I think one moment in time here is consolidating things with Jerry and having him build out this large scale effort here. So, I mean, it's been going on for a long time, but I think what's really cool about research is there's that aha moment. There's that particular point in time where something surprising happens and things really click together. Are there any times for you all when you had that aha moment? Like we trained GPT-2, GPT-3, GPT-4. There was the first moment when the moment was hot off the press. We started talking to the model and people were like, wow, this model is really great. And starting doing something like that. And I think that there was a certain moment in our training process where we trained, like put more compute in our L than before and trained first of all, generating coherent chains of thought. And we said, wow, this looks like something meaningfully different than before. I think for me, this is the moment. Wow. Related to that, when we think about like training a model for reasoning, one thing that immediately jumps to mind is you could have humans write out their thought process and train on that. When aha moment for me was like when we saw that if you train the model using RL to generate and hone its own chain of thoughts, it can do even better than having humans write in the thought for it. And that was an aha moment that you could really scale this and explore models reasoning that way. For a lot of the time that I've been here, we've been trying to make the models better at solving math problems, as an example. And we've put a lot of work into this and we've come up with a lot of different methods. But one thing that I kept like every time I would read these outputs from the models, I'd always be so frustrated. The model just would never seem to question what was wrong or when it was making mistakes or things like that. But one of these early O1 models when we trained it and we actually started talking to it, we started asking these questions and it was scoring higher on these math tests we were giving it. We could look at how it was reasoning and you could just see that it started to question itself and have really interesting reflection. And that was a moment for me where I was like, wow, like we've uncovered something different. This is going to be something new. And it was just like one of these coming together moments that that was really powerful. So when you read the thoughts, does it feel like you're watching a human or does it feel like you're watching a robot? It's like a spiritual experience. It's a spiritual experience, but then you can empathize with the model. You're like, oh, that's a mistake that a lot of people would make or you can see it sort of questioning common conventions. And yeah, it's spiritual, but like oddly human in its behavior. It was also pretty cool at some point when we have seen in cases where there was like a limited amount of thinking allowed for the model that just before the timeout, the model was like, I have to finish it now. And so here's the answer. I spent a lot of time doing competition math when I was young and that was really my whole reason for getting into AI was to try and automate this process. And so it's been very like a huge full circle moment for me to see the model actually be able to follow through, like very close to the same steps I would use when solving these problems. And it's not exactly the same chain of thought, I would say, but very, very relatable. It's also really cool to know it's believable that these models, they are getting on the cusp of really advancing engineering and science. And if they seem to be solving the problems, you know, maybe we can call ourselves experts, hard for us, then maybe they will be even hard for some other experts and could advance science. So we've talked a lot about some of the great moments and the times and everything just clicked. What are some of the hurdles? What are some of the places where it was actually really hard to make things work? Training large models is fundamentally a very, very hard thing to do. And there are like thousands of things that can go wrong and there are at least like hundreds that did go wrong in every training run. So I want everyone here to put a lot of blood, sweat and tears in training those things and figuring out how to keep them, continue learning and improving on a path that is actually the path of success is very narrow and the ways of failure are plentiful. It's like imagine like having the center for launching a rocket to the, let's say, some planet moon or so. And if you are off by one angle, you won't arrive at the destination. And that's our job. So the model we said is very good, oftentimes better than humans, like has equivalent of several PhDs. And that is sometimes a challenge because we have to often go and verify that the model isn't going off the rails, that we're doing something self-sensible and it started taking some serious time as we scale the model. We were saturating out all the industry grade evals and we don't know what to look for next. So that is also a challenge. I do think all of these things we ran into, it's also been one point of fulfillment. It's like every time you have a puzzle, it's like another hurdle for this team to overcome. And I'm really glad with all the little hurdles that we've overcome. So what are some of the ways you tested the models? Did you have any favorite questions that you saw the model get better at? How many Rs are in strawberries? For whatever reason, the Chagy PT wasn't able to solve this question reliably. But O-1, we did like a year and a half work, like a large number. And now we can count the number of Rs in strawberries. We should have just hard coded that rule. Reliably. I have this habit, which I think other people here do too, of whenever you go on Twitter and you see some post that's like, large language models can't do this, you copy and paste it in and then you say, confirm that our large language models can do this. To give people a sense of what they can use the model for, I'd love to hear some of the ways that you use O-1. So one way I've been using O-1 is for obviously coding. And a lot of my job is about coding. So more and more, I focus on the problem definition and use this what's called a TDD, test driven development. So instead of writing the code that implements the functionality, I focus on writing say, unit test that specify what is correct behavior of this piece of code to pass. And so because I can focus on more of that and then pass it on to O-1 to really implements I can focus on what's important, what's a high level problem to solve and so on. So this has been really an important way of shifting my focus. And another area is debugging. So now when I get some error messages, I just pass it to O-1 and then it just prints out something. Sometimes it solves right away. Even if it doesn't, it at least gives some better questions to ask and provides some ways to think about this problem better. So it has been a really important change of working for me and I hope this helps others too. I like using O-1 more and more for learning. The more I ask it's like various complex technical subjects, I find hallucinate less and explain better those concepts on previous models. For me, I like to use O-1 as like a brainstorming partner. So that can range from anything from like how to solve some very specific ML problem, machine learning problem to like how to write a blog post or a tweet. So for example, I recently wrote a blog post about language model evaluations and I was asking O-1 about ideas for the structure of the blog post, pros and cons of certain benchmarks and even the style of the writing. And I think because it's able to think before it gives the final answer, it's able to connect ideas better. It can revise and critique candidate ideas and things like that. Yeah, I think if you need like a, you know, you have some short text and you want it more creative, something really different, that's a great use to like give me five different ideas. Also, if you have just sort of like some unstructured thoughts, it's a really brilliant thought partner. So you have like some ideas, it's like, well, how should I connect these things? What am I missing? And through its final answers and through sort of reading its like thought process, it can really lead to like much better results for you. Yeah, I use it to try out a bunch of our internal secret ideas and actually tries to improve it. Yeah, for standalone projects, it's great. Like, I had to add the GitHub plugin. I know nothing about adding GitHub plugins and I just said like, hey, I want GitHub plugin that displays this and this information about the PR and like, yeah, just produce the code. I just like, like, you know, I would just ask it like, okay, so where do I need to paste this code? I don't even know. It's just like, yeah, you paste it here. I think for a lot of people, it's hard to really fill the AGI until you see the models do something better than humans can at a domain that you really care about. And I think, you know, for Go players and chess players that would have come a few years earlier and for a lot of us that like really value math and coding, I think we're starting to feel that now. I want Mams to be proud of us. So are there any parts of this project, anything that really needed to be done, but, you know, people might not realize how important it is? Yes, so I think building large-scale, reliable infrastructure for to run our biggest flagship model training grounds, as well as doing research experiments is something that is not as exciting as doing research itself, but has to be done and it has a tremendous impact on the success on the entire project. I think there is something special in OpenAI about how we structure our research in that we value algorithmic advancements in the same way as building reliable large-scale systems and building data sets that are needed either way for training those models. I'm really proud of OpenAI in that way. I think that has been a consistent pattern throughout many of our big projects. Every time we scale a new thing up, another order of magnitude, we see another host of problems, both algorithmic and infrastructure, and we've definitely built a capacity to advance them both with a lot of focus. I feel the final model is just like literally a beautiful piece of art, right? In order to make it work, we have to make sure that every step has work, right? You know, we find some any time to solve it, right? I think that's really how OpenAI operates and I'm very proud to work on here. And I also must say there's like a really not only brilliant people are here, but also kind hearted. It's just fun to me to work over here and I'm grateful to my colleagues. So, you know, code with me, per code with me, hang out with me, eat lunch with me, like speak with the model with me. So what's it like to work on the Strawberry team? You can have your brilliant ideas, but most of the time you spend on like running them and not running and failing and then it's very good to have people very close by in your office that you can ask for help with whatever failed last time because I mean most of the time you spend your time debugging things that didn't work. And having people who can help you is... Speaking of this help, we had many times when we were trying to debug this for like a week. And then passing by Wenda and then like ask it and then like he just sold it right away. He started calling it a Wenda blessing and then blessing for other people. And that has been really, really effective. And I stopped like thinking about it's too stupid to ask and just ask right away. One of the things I like really appreciate about working on OpenAI is that from every big project like this, we like really learn, right? I think like from DOTA we learn the importance of engineering, from GPT-4 we learn the importance of research and we keep iterating like this. And the effect of that is that like now the Strawberry team is again the best big research project team yet because it's built on all of the things we've learned from the previous projects. And it really like you can like really see working here like people really like started developing, being developed very good intuition. Like when do you hack something? Where do you like need to develop stronger fundamentals? Like when do you start overnight? Where do you actually like take a weekend off and like come with a fresh mind to this particular problem? Like I think like it's really amazing to observe this progress we make as a company. Yeah, one thing I've liked is just how organic this project has felt. The ideas have come literally from everywhere on this team and people feel empowered to just like, hey, here's an idea I really believe in and it's the thing that I'm going to push. And also people are just willing to get their hands dirty. I feel like there have been a lot of deadlines, some self-imposed, but we've all really come together and you know, been willing to put in that work to make it happen. This project really demonstrated the power of momentum where we get initial good results and more and more people get excited about particular field and particular research. They try to contribute their new ideas. Those new ideas work even better. And then the things started snowballing and getting more and more momentum on itself and people just believing that this is the right thing to do and we should continue pushing this research. Related to that, I think we have a very, lots of very smart people, but also like very opinionated people. But people are always willing to like update their opinions once you see results to the contrary. And I think that's like make things really fun. It's kind of cool to be in that place that's a combination of like a brilliant scientist and engineers and folks who can like build out like incredible systems. It's very humbling. So one thing I remember a few months ago, I remember the model was very smart, but it was also kind of boring. So what was it like to give the model a personality? Yeah, so that's interesting. I remember I asked model about the meaning of life and it gave me an answer 42, which is not that bad of an answer. And, you know, it's kind of similarity when I asked model, you know, what is love? It told me, oh, it is like a strange human feeling. And once we actually gave model personality, made it actually work with chat, then the answers start being quite interesting. That day, you know, I asked about the love. It told me, you know, there's like a romantic love, familial love, self-love, non-conditional love, conditional love. And it became more useful and also more fun. The funnest moment is that I ask the exact same question and you try to define love with algebra. I'm sure you ask enough nerd questions. So what's the story of O1 Mini? How did that come to be? So the motivation is that we want to bring the O1 series to broader audience with a budgetary cost. So we created O1 Mini, which was designed to be like a minimal demonstration of the whole O1 pipeline or the framework. We make it a stand reasoning specialist, which may not necessarily know the birth date of our favorite celebrity, but really truly understands like how to do reasoning effectively and truly has a lot of intelligence. The model is actually really smart. It's like much smarter than our previous best model for all and also almost on par with our best model O1, but only comes with a fraction of cost and latency. It does have the limitation that you may not know a lot of the knowledge in the outside world, which is not about science or technology, but you try to make it roughly on par with our previous best model, like for O1 Mini, and we are working to improve it further. So I'm super excited for our external users who just try it out for this lightning experience of reasoning and thinking. So what motivates you to do your research? I just find it fascinating that in this world you have these things that can do intelligence and reasoning and they're much smaller than you'd think and they can do this in different ways. It's just super fascinating. Good things in life take time and our models just tend to answer too quickly. And eventually we want to have models that can do, for example, research for months or years. And I feel like this is the first step in the direction of models that can think very long for about one problem. And now we're at the level of minutes. And I think it's just the first step on a long path that hopefully takes us to models that can think for months or years as time goes by. It feels very meaningful that I, together with a small number of people, can have some substantial positive impact on the world. And also it's fun. Day to day it's just fun. I like, you know, speaking to the computer. I like starting a job on the cluster. I very much enjoy collaboration. It's just beautiful. I really like our models to be useful. And I think technology has a chance and a promise to improve human life. And I like our models to do work for us, to help us with our day to day problems and giving them ability to reason. It allows them to do for us things that they just couldn't before that will allow us to spend our time more productively. Yeah, I'm very excited about this. I mean, I think these sort of paradigms unlock things that the models couldn't do before. So it's not just like answering some sets of queries a little bit better, but it's actually getting to a point where through planning, through error correction, it's able to just unlock like new capabilities and the ability to produce new knowledge in the world for like science, for discovery, I think is one of the most exciting pieces for this. And I think in some short amount of time, it's going to become like a larger and larger contribution or contributor to its own development. And I think that's like a really exciting regime. I think some of the people on this team, we were math or coding Olympiad participants in the past. And there is this huge personal motivation to create a system that can beat us and do best. And I think the second thing really kind of echoes the point that JT and Leo made. You know, I do think reasoning is a much more powerful primitive than people give it credit for. You know, when you think about kind of accomplishing tasks reliably, really that fundamental primitive has to be reasoning. You're going to hit bottlenecks and you're going to have to navigate your way around them. So I'm really excited for that. I think AI researchers job is to find the way to put more compute in. And hardware people have been doing so good of a job that the cost has been going down exponentially for a very long time. And we don't have much time to find another way to put in more compute. And it's kind of like a weight on my shoulders is getting larger and larger. And this new paradigm really finds a way to unload that for probably a long time. Is there anything else you've observed as we've been going through this project for the whole time we've been doing it? Anything else that's worth calling out? I think an interesting meta observation that we've had is every model that we train is like a little bit different. It has its own quirks and it's almost like artisanal. Because when you look at a model that can do so many different tasks, each model you train won't be exactly the same performance at each task. So it might be better at some tasks and worse at others. And so there's this uniqueness or like personality to every model that is almost like a little bit beautiful. Thank you and congrats on releasing this.

#要約