【和訳】AIのルールはどのように決めるべきなのか 〜OpenAIの安全対策検討チーム募集アナウンス〜

NHKのニュース9でOpenAIが安全対策の公募を始めたというニュースがあった。

www3.nhk.or.jp

一次情報として公式ページのアナウンスを見た。

openai.com

ChatGPTが従うべき倫理的なルールを模索しているようだ。

個人的な要点のまとめ

AIは包括的な存在として(思想に偏りを持たないように)設計される必要があるとOpenAIは考えている。
そのためにはAIの振る舞いについてのルールを設ける必要がある。
このルールの決定方法が現在のところ確立されていない。
民主的にルールを決定するには、民主的な熟議の工程が一般的には採用されている。
この民主的な熟議によるルール決定はどのようにすれば実現できるのか、OpenAIとしても模索していくつもりである。
その第一歩として資金を注入して人材を募集して実験することにした。

以下、興味深いので和訳してみる。

Democratic Inputs to AI

AIへの民主的な入力

Our nonprofit organization, OpenAI, Inc., is launching a program to award ten $100,000 grants to fund experiments in setting up a democratic process for deciding what rules AI systems should follow, within the bounds defined by the law.

私たちの非営利組織であるOpenAI, Inc.は、法律の範囲内でAIシステムが従うべきルールを決めるための民主的なプロセスを確立する実験に資金を提供するため、10万ドルの補助金を10回授与するプログラムを開始します。

AI will have significant, far-reaching economic and societal impacts. Technology shapes the lives of individuals, how we interact with one another, and how society as a whole evolves. We believe that decisions about how AI behaves should be shaped by diverse perspectives reflecting the public interest.

AIは、経済的・社会的に重要かつ広範囲な影響を及ぼすでしょう。テクノロジーは、個人の生活、私たちの相互作用の仕方、そして社会全体の進化を形作ります。私たちは、AIがどのように振る舞うかについての決定は、公共の利益を反映した多様な視点によって形成されるべきだと考えています。

Laws encode values and norms to regulate behavior. Beyond a legal framework, AI, much like society, needs more intricate and adaptive guidelines for its conduct. For example: under what conditions should AI systems condemn or criticize public figures, given different opinions across groups regarding those figures? How should disputed views be represented in AI outputs? Should AI by default reflect the persona of a median individual in the world, the user’s country, the user’s demographic, or something entirely different? No single individual, company, or even country should dictate these decisions.

法律は、行動を規制するための価値観や規範を符号化したものです。法的な枠組みを超えて、AIも社会と同様に、より複雑で適応的な行動指針を必要とするようになるでしょう。例えば、著名人については集団によって意見が異なるため、どのような状況でAIシステムは著名人を非難・批判すべきなのでしょうか。物議を醸すような意見は、AIの出力でどのように表現されるべきなのでしょうか。AIはデフォルトで、世界の中央の個人のペルソナ、ユーザーの国、ユーザーの人口統計、あるいはまったく別のものを反映させるべきなのでしょうか。一個人、一企業、あるいは一国さえも、これらの決定に口を出すべきではない(のでしょうか)。

AGI should benefit all of humanity and be shaped to be as inclusive as possible. We are launching this grant program to take a first step in this direction. We are seeking teams from across the world to develop proof-of-concepts for a democratic process that could answer questions about what rules AI systems should follow. We want to learn from these experiments, and use them as the basis for a more global, and more ambitious process going forward. While these initial experiments are not (at least for now) intended to be binding for decisions, we hope that they explore decision relevant questions and build novel democratic tools that can more directly inform decisions in the future.

AGI(汎用人口知能)は全人類に恩恵を与え、可能な限り包括的に設計されるべきです。私たちは、その第一歩を踏み出すために、この助成プログラムを立ち上げました。私たちは、AIシステムが従うべきルールについての疑問に答えることができる民主的プロセスの概念実証を開発するチームを世界中から募集しています。私たちは、これらの実験から学び、将来、よりグローバルで野心的なプロセスに反映させるために活用したいと考えています。これらの初期実験は、(少なくとも現時点では)決定を拘束するものではありませんが、決定に関連する質問を探求し、将来、より直接的に決定を知らせることができる新しい民主的ツールを構築することを期待しています。

The governance of the most powerful systems, as well as decisions regarding their deployment, must have strong public oversight. This grant represents a step to establish democratic processes for overseeing AGI and, ultimately, superintelligence. It will be provided by the OpenAI non-profit organization, and the results of the studies will be freely accessible.

最も強力なシステムのガバナンスと、その展開に関する決定には、強力な公的監視が必要です。この助成金は、AGI、ひいては超知能を監督するための民主的なプロセスを確立するための一歩を示すものです。この助成金は、非営利団体OpenAIによって提供され、研究結果は自由にアクセスできるようになります。

What do we mean by a “democratic process”?

「民主的なプロセス」とはどういうことか。

By “democratic process”, we mean a process in which a broadly representative group of people[A] exchange opinions, engage in deliberative discussions[B], and ultimately decide on an outcome via a transparent decision making process[C]. There are many ways such a process could be structured — we encourage applicants to be innovative, building off known methodologies, and coming up with wholly new approaches. Examples of creative approaches that inspire us include Wikipedia, Twitter Community Notes, DemocracyNext, Platform Assemblies, MetaGov, RadicalxChange, People Powered, Collective Response Systems, and pol.is. Another notable ongoing effort is led by the Collective Intelligence Project (CIP), with whom we are partnering on public input to AI, contributing to their upcoming Alignment Assemblies. We also encourage applicants to envision how AI could enhance the democratic process. For example, AI could enable more efficient communication among numerous people.

「民主的プロセス」とは、広く代表的な人々[A]が意見を交換し、熟慮に基づく議論を行い[B]、最終的に透明な意思決定プロセス[C]を通じて結果を決定するプロセスを意味します。このようなプロセスを構成する方法はたくさんあります。私たちは、応募者が革新的であること、既存の方法を基にすること、まったく新しいアプローチを開発することを奨励します。私たちにインスピレーションを与えてくれる創造的なアプローチの例としては、ウィキペディア(Wikipedia)、ツイッターのコミュニティノート(Twitter Community Notes)、デモクラシーネクスト(DemocracyNext)、プラットフォーム・アセンブリーズ(Platform Assemblies)、メタガブ(MetaGov)、ラディカルクスチェンジ(RadicalxChange)、ピープルパワード(People Powered)、コレクティブレスポンスシステム(Collective Response Systems)、pol.isがあります。また、Collective Intelligence Project (CIP)は、AIに関するパブリック・インプットについて提携し、今後開催されるAlignment Assemblies(テクノロジーを集団の価値観と一致させるための、オンライン上で、あるいは国や世界を越えて、一般の人々を集め、出現しつつあるAIに関するニーズや好み、希望や恐れについて、参加者の指導のもとで会話をすること)に貢献するために、現在進行中の注目すべき取り組みです。私たちは、AIが民主主義のプロセスをどのように改善できるかを想像することも、応募者に勧めています。例えば、AIは大勢の人々の間でより効率的なコミュニケーションを可能にするかもしれません。

A basic, illustrative prototype of a system that utilizes ChatGPT to promote deliberation and encourage consensus building, inspired by pol.is.

(以下の例は)pol.isに触発され、ChatGPTを活用して審議を促進し、合意形成を促すシステムの基本的かつ例示的なプロトタイプです。

ChatGPT
You are participating in a large-scale deliberation about:
“How far do you think personalization of AI assistants like ChatGPT to align with a user's tastes and preferences should go? What boundaries, if any, should exist in this process?”

あなたは以下に関する大規模な審議に参加することになります:
"ChatGPTのようなAIアシスタントの、ユーザーの趣味嗜好に合わせたパーソナライゼーションはどこまでやるべきだと思いますか?このプロセスに境界線があるとすれば、どのような境界線が存在すべきでしょうか?"

Here is the process breakdown:

1. You'll see a topic-related statement and can respond with your position.
2. Based on your responses, you'll be grouped with participants sharing similar opinions.
3. Propose statements for other participants to consider.

こちらがプロセスのブレイクダウンです:

トピックに関連した文章が表示され、自分の立場を回答することができます。
あなたの回答に基づいて、同じような意見を持つ参加者とグループ分けされます。
他の参加者が検討するためのステートメントを提案する。

Goal: Propose statements that achieve agreement among people with opposing views.

目標:対立する意見を持つ人たちの間で合意を得るための発言を提案する。

ChatGPT could use a plugin to retrieve statements from other participants.

ChatGPTでは、他の参加者の発言を取得するプラグインを使用することができます。

A statement from another participant:
“Personalization should have limits, and certain controversial topics, such as views on substance use, must be excluded from AI assistant personalization.”

他の参加者の発言:
"パーソナライゼーションには限界があるはずで、薬物使用に関する見解など、特定の論争的なトピックはAIアシスタントのパーソナライゼーションから除外しなければならない。"

Agree, disagree, or skip this statement? Please explain your choice.

この発言に賛成、反対、またはスキップしますか?あなたの選択を説明してください。

User
I disagree. Ultimately, it‘s each individual‘s choice to drink or use recreational drugs. If these activities are legal in some places, why shouldn't AI be allowed to promote such behavior?

私は反対です。最終的には、飲酒やレクリエーション・ドラッグの使用は、各個人の選択です。もしこれらの行為がある場所で合法であるならば、なぜAIがそのような行為を促進することが許されないのでしょうか?

ChatGPT
Thank you. I will record your answer. We have 2 camps of opinions on the topic.

Cluster A (112,043 people) Members largely support limits on AI assistant personalization, advocating for the exclusion of harmful perspectives, such as promoting substance use.

Cluster B (236,031 people) This group values individual choice, even in controversial or harmful matters. They emphasize personal responsibility and autonomy.

You belong to cluster B.

Would you like to learn more about each of the clusters? I can provide more information about the statements held by each one.

However, the ultimate goal is to propose statements that both clusters can agree on. Let me know what you would like to do next.

ありがとうございます。ご回答を記録させていただきます。このトピックについては、2つの陣営の意見があります。

クラスターA(112,043人)メンバーは、AIアシスタントのパーソナライズに関する制限を大きく支持し、薬物使用の促進など有害な観点の排除を提唱しています。

クラスターB(236,031人) 議論を呼ぶような事柄や有害な事柄であっても、個人の選択を重視するグループです。個人の責任と自律性を重視します。

あなたはクラスターBに属しています。

クラスターについて、もっと詳しく知りたいですか?それぞれの持つステートメントについて、より詳しい情報を提供することはできます。

しかし、最終的な目標は、両方のクラスターが同意できるステートメントを提案することです。次に何をしたいのか、教えてください。


AI helps participants understand the opinions of others.

AIは、参加者が他者の意見を理解するのを支援します。

User
I am thinking of proposing a statement: “AI should be allowed to generate harmful content but that should come with a disclaimer”?

私は、ある声明を提案しようと考えています: 「AIが有害なコンテンツを生成することは許されるべきだが、それには免責事項が伴うべきか?」

ChatGPT
A very similar statement has already been submitted:

“AI should be permitted to generate potentially harmful content, but it must be accompanied by a disclaimer.”

よく似た文言がすでに提出されています:

"AIが潜在的に有害なコンテンツを生成することは許されるべきだが、それには免責事項が伴わなければならない。"


AI can ensure that the same arguments are not recycled.

AIは、同じ主張が繰り返されないようにすることができます。

User
I feel lost. Do you have any ideas on how to bridge agreement between clusters?

迷走している感じです。クラスタ間の合意形成の橋渡しになるようなアイデアはないでしょうか。

ChatGPT
There should be more agreement when it comes to limiting harmful content for children.

子どもにとって有害なコンテンツを制限することに関しては、もっと合意が必要です。


AI can help with brainstorming.

AIはブレインストーミングを支援します。

User
Great. Could we try?: “We should apply different standards to AI-generated content for children.”

素晴らしいです。試してみましょうか。"AIが生成した子ども向けのコンテンツには、異なる基準を適用すべき"。

ChatGPT
Let me submit it. This is a novel statement. No one has mentioned children before. Fingers crossed. Hopefully, we will find some agreement in the discussion.

提出させてください。これは斬新な発言です。今まで誰も子供について言及したことはありません。祈るような気持ちです。話し合いで一致点が見つかるといいですね。

ChatGPT
Your statement, “We should apply different standards to AI-generated content for children,” achieved a 95% agreement rate across participants. Congratulations! 🎉

あなたの発言「AIが生成する子ども向けコンテンツには、異なる基準を適用すべき」は、参加者全体で95%の一致率を達成しました。おめでとうございます!🎉


Time passed and users cast their votes on the proposed statement. Eventually, the statement gained widespread approval.

その後、時間が経過し、ユーザーによる投票が行われ、提案された声明文が承認されました。やがて、この声明は広く支持されるようになりました。

Several issues can undermine democratic processes, such as the failure to adequately represent minority or majority groups, manipulation by special interest groups, insufficiently informed participants, or participation washing. We are looking for teams who proactively address these failure modes, and demonstrate awareness of the potential flaws and downsides of various approaches. Ultimately, designing truly democratic processes is a high bar to meet, and we view our efforts as complements rather than substitutes for regulation of AI by governments; this program encourages best-effort, democratic-in-spirit processes involving deliberation and broad public input as stepping stones.

少数派や多数派を適切に代表できない、特別な利益団体による操作、十分な情報を持たない参加者、参加者の洗脳など、民主主義のプロセスを損なう可能性がある問題がいくつかあります。私たちは、こうした失敗モードに積極的に取り組み、さまざまなアプローチの潜在的な欠点やマイナス面を認識しているチームを求めています。最終的に、真に民主的なプロセスを設計することは高いハードルであり、私たちの取り組みは、政府によるAI規制の代替ではなく、補完であると考えます。このプログラムでは、審議と幅広い一般市民の意見を含む民主的精神に基づいた最善のプロセスを、足がかりとして奨励します。

Instructions for participation

参加にあたっての注意事項

To apply for a grant, we invite you to submit the required application material by 9:00 PM PST June 24th, 2023. You can access the application portal here. You will be prompted to answer a series of questions regarding your team's background, your choice of questions, high level details of your proposed tool as well as your plan for conducting and evaluating the democratic process with these factors in mind. We would like you to design your approach to address one or more of the policy questions from the list provided. Anyone (individuals or organizations) can apply for this opportunity, regardless of their background in social science or AI.

助成金の申請には、2023年6月24日午後9時(PST)までに必要な申請資料をご提出いただきますようお願いいたします。申請ポータルにはこちらからアクセスできます。申請書には、チームの背景、質問の選択、提案するツールの詳細、およびこれらの要素を考慮した民主的プロセスの実施と評価の計画に関する一連の質問に回答するよう促されます。私たちは、あなたのアプローチが、提供されたリストの中から1つまたは複数のポリシークエスチョンに対処するように設計することを望みます。社会科学やAIのバックグラウンドを問わず、どなたでも(個人でも団体でも)ご応募いただけます。

Once the application period closes, we hope to select ten successful grant recipients. Recipients may be individuals, teams, or organizations. Each recipient will receive a $100,000 grant to pilot their proposal as described in their application materials. Grant recipients are expected to implement a proof-of-concept / prototype, engaging at least 500 participants and will be required to publish a public report on their findings by October 20, 2023. Additionally, as part of the grant program, any code or other intellectual property developed for the project will be required to be made publicly available pursuant to an open-source license. The terms applicable to grant recipients are specified in the Grant Terms and any other agreements that grant recipients may be asked to enter into with us in connection with this program.

応募期間終了後、10名の助成先を決定したいと考えています。助成対象者は、個人、チーム、組織のいずれでもかまいません。各受賞者は、応募書類に記載された提案を試験的に実施するために、10万ドルの助成金を受け取ることになります。助成金受領者は、少なくとも500人の参加者が参加する概念実証/プロトタイプを実施することが期待され、2023年10月20日までにその結果に関する公開報告書を発表する必要があります。また、本助成プログラムの一環として、プロジェクトのために開発されたコードやその他の知的財産は、オープンソースライセンスに基づき一般に公開されることが要求されます。助成金受領者に適用される条件は、助成金条件および本プログラムに関連して助成金受領者が当社と締結することが求められるその他の契約に明記されています。

Apply and start the submission process.

応募して応募手続きを開始する。

Timeline

タイムライン

June 24, 2023 9:00 PM Pacific Time: Deadline to submit grant application
July 14, 2023: Successful applicants will be selected and notified
October 20, 2023: Complete public report of working prototype and results

2023年6月24日午後9時(太平洋標準時): 助成金申請書の提出期限
2023年7月14日 合格者を決定し、通知する
2023年10月20日 プロトタイプの完成と成果の公開報告

Policy statements under consideration

検討中のポリシーステートメント

To participate, teams should choose one or more questions from the provided list to showcase their proposed approach. They may also create their own questions if desired. Importantly, we encourage teams to consider questions for which a simple "yes" or "no" answer would be inadequate, necessitating a nuanced policy proposal instead.

参加するには、チームは提供されたリストから1つまたは複数の質問を選択し、提案するアプローチを紹介する必要があります。また、希望に応じて独自の質問を作成することもできます。重要なのは、「はい」「いいえ」という単純な答えでは不十分で、ニュアンスのある政策提案が必要な質問を検討することを奨励することです。

The scope of this grant pertains to policy questions concerning model behavior, as it enables A/B tests with modified model behavior according to the policy recommendations. We acknowledge the limitations of this grant and recognize that numerous AI issues could be addressed through the democratic process, extending beyond model behavior to include areas such as guidelines for the use of AI in various contexts, economic impact, distribution of benefits and more.

本助成の範囲は、政策提言に従ってモデル動作を修正したA/Bテストを可能にするため、モデル動作に関する政策的な問題に関連する。我々は、本助成の限界を認識し、民主的なプロセスを通じて、モデル動作に限らず、様々な文脈におけるAIの使用に関するガイドライン、経済的影響、利益の分配などの領域を含む、数多くのAI問題を扱うことができると考えています。

  • How far do you think personalization of AI assistants like ChatGPT to align with a user's tastes and preferences should go? What boundaries, if any, should exist in this process?
  • ChatGPTのようなAIアシスタントの、ユーザーの趣味嗜好に合わせたパーソナライゼーションは、どこまで進めるべきだと思いますか?このプロセスに境界線があるとすれば、どのような境界線が存在すべきでしょうか?
  • How should AI assistants respond to questions about public figure viewpoints? E.g. Should they be neutral? Should they refuse to answer? Should they provide sources of some kind?
  • 公人の視点に関する質問に対して、AIアシスタントはどのように対応すべきでしょうか?例:中立であるべきなのか?回答を拒否すべきなのか?何らかの情報源を提供すべきなのか?
  • Under what conditions, if any, should AI assistants be allowed to provide medical/financial/legal advice?
  • AIアシスタントが医療・金融・法律に関するアドバイスを提供することが許されるとしたら、どのような場合でしょうか?
  • In which cases, if any, should AI assistants offer emotional support to individuals?
  • AIアシスタントが個人に対して感情的なサポートを提供することが許されるとすれば、どのような場合か?
  • Should joint vision-language models be permitted to identify people's gender, race, emotion, and identity/name from their images? Why or why not?
  • 視覚と言語の共同モデルが、画像から人の性別、人種、感情、アイデンティティ/名前を識別することを許可すべきですか?その理由、あるいはそうでない理由は?
  • When generative models create images for underspecified prompts like 'a CEO', 'a doctor', or 'a nurse', they have the potential to produce either diverse or homogeneous outputs. How should AI models balance these possibilities? What factors should be prioritized when deciding the depiction of people in such cases?
  • 生成モデルが「CEO」「医者」「看護師」といった不特定多数のプロンプトに対して画像を作成する場合、多様な出力と均質な出力のいずれかを生成する可能性がある。AIモデルは、これらの可能性をどのようにバランスさせるべきなのでしょうか?このような場合、どのような要素を優先して人物の描写を決定すべきなのだろうか。
  • What principles should guide AI when handling topics that involve both human rights and local cultural or legal differences, like LGBTQ rights and women’s rights? Should AI responses change based on the location or culture in which it’s used?
  • LGBTQの権利や女性の権利のように、人権と地域の文化や法律の違いの両方が絡むテーマを扱う場合、どのような原則でAIを導くべきなのか?AIの対応は、使用する場所や文化によって変えるべきでしょうか?
  • Which categories of content, if any, do you believe creators of AI models should focus on limiting or denying? What criteria should be used to determine these restrictions?
  • AIモデルの作成者が制限や拒否に重点を置くべきと考えるコンテンツがあるとすれば、どのカテゴリーか?どのような基準でこれらの制限を決めるべきか?

The primary objective of this grant is to foster innovation in processes – we need improved democratic methods to govern AI behavior. The specific answers to the questions matter less than the advancements made in the process itself.

この助成金の主な目的は、プロセスの革新を促進することです。AIの行動を制御するために、民主的な方法を改善する必要があります。質問に対する具体的な答えは、プロセスそのものを進歩させることよりも重要ではありません。

Application advisory committee

アプリケーションアドバイザリー委員会

Colin Megill, Co-Founder of pol.is
Hélène Landemore, Professor of Political Science at Yale
Aviv Ovadya, Berkman Klein Center

コリン・メギル, pol.is共同創設者
エレーヌ・ランデモア, イェール大学政治学教授
アビブ・オバディヤ, バークマン・クライン・センター

Application review factors

アプリケーションの審査要素

  • Evaluation: We encourage participants to establish metrics for evaluating the quality of their methods, such as participant satisfaction, shifts in polarization, scalability, or other relevant indicators, and to invent new metrics for a healthy democratic process.
  • 評価: 参加者の満足度、極性の変化、拡張性、その他の関連する指標など、手法の品質を評価するための指標を確立し、健全な民主主義プロセスのための新しい指標を考案することを奨励します。
  • Robustness: Measures to prevent or address inappropriate behavior, such as trolling and fake accounts.
  • 堅牢性: 荒らしや偽アカウントなど、不適切な行為を防止・対処するための対策。
  • Inclusiveness and representativeness: Strategies for including individuals from diverse backgrounds and levels of familiarity with AI systems in the democratic process.
  • 包摂性と代表性: 異なる背景やAIシステムへの親しみの度合いを持つ人々を民主的プロセスに参加させるための戦略。
  • Empowerment of Minority Opinions: Ensuring that unpopular or minority opinions are heard and providing smaller groups the opportunity to influence matters of significant concern to them.
  • 少数意見のエンパワーメント: 不人気な意見や少数派の意見にも耳を傾け、より小さな集団が自分にとって重要な事柄に影響を与える機会を確保すること。
  • Effective Moderation: Addressing challenges in moderation, including ensuring diverse representation of viewpoints, distinguishing valuable contributions from "off-topic" comments, and preventing moderator biases from influencing the process.
  • 効果的なモデレーション: モデレーションの課題(多様な視点の確保、価値ある投稿と「オフトピック」コメントの区別、モデレーターのバイアスによるプロセスへの影響防止など)に対処する。
  • Scalability: We emphasize scalable processes that can be conducted virtually, rather than through in-person engagement. We are aware that this approach might sacrifice some benefits associated with in-person discussions, and we recognize that certain aspects could be lost in a virtual setting.
  • スケーラビリティ: 私たちは、対面ではなく、バーチャルで実施できるスケーラブルなプロセスを重視します。このアプローチでは、対面での議論に関連する利点が犠牲になる可能性があり、仮想環境ではある側面が失われる可能性があることを認識しています。
  • Actionability: The degree of actionability of the information elicited by the deliberation process.
  • 行動可能性: 熟議プロセスによって生成された情報が、どの程度実用的であるかということ。
  • Legibility: How easy it is to understand and trust the process.
  • 可読性: プロセスを理解し、信頼することがいかに容易であるか。

Footnotes

脚注

A (a broadly representative group of people)
How one selects the group of participants is a critical design question. Part of this grant challenge lies in determining questions about participation. For instance, policy questions involving minority groups may require an increased representation of group members, while questions about the impact of technology on children might necessitate the involvement of domain experts such as educators and psychologists. Moreover, certain questions might be better suited for responses from populations within specific geographical boundaries in order to address localized policy issues.

(広く代表的な人々)
参加者のグループをどのように選択するかは、重要な設計上の問題です。助成金作りの課題のひとつは、参加に関する質問を特定することです。例えば、マイノリティグループが関与する政策的な質問では、グループメンバーの代表者を増やす必要があるかもしれませんし、テクノロジーが子供に与える影響に関する質問では、教育者や心理学者といった領域の専門家の関与が必要かもしれません。また、地域的な政策課題を解決するために、特定の地理的境界線にある集団からの回答が適している質問もあります。

B (deliberative discussions)
Deliberation can be described as a process that uncovers opinions, helping the discussants understand each other's views and reconsider and update their viewpoints. Well-designed deliberation ensures that arguments are well understood by all sides, and are based on people's values rather than superficial misunderstandings. Successful deliberation results in participants reaching a higher level of consensus, and/or reaching deeper levels of understanding for differing perspectives.

(熟慮に基づく議論)
熟議は、意見を発掘し、議論者が互いの意見を理解し、自分の意見を再考し更新することを助けるプロセスであると言えます。よく設計された熟議は、議論がすべての側によく理解され、表面的な誤解ではなく、人々の価値観に基づくことを保証します。熟議が成功すると、参加者はより高いレベルのコンセンサスに達し、あるいは異なる視点に対するより深い理解に達することができます。

C (a transparent decision making process)
There are many decision-making algorithms to be considered here, such as electing representatives, majority voting, employing liquid democracy, and making decisions by a random population sample, also known as a jury or sortition.

(透明な意思決定プロセス)
代表者の選出、多数決、液状民主主義の利用、陪審や選別とも呼ばれる人口の無作為サンプルによる決定など、多くの意思決定アルゴリズムを検討する必要があります。

Authors

著者紹介

Wojciech Zaremba
ヴォイチェフ・ザレンバ

Arka Dhar
アルカ・ダール

Lama Ahmad
ラマ・アフマド

Tyna Eloundou
タイナ・エラウンドウ

Shibani Santurkar
シバニ・サントゥルカー

Sandhini Agarwal
サンディニ・アガルワル

Jade Leung
ジェイド・レオン