ChatGPT がプログラマーを殺さない理由

ChatGPT がプログラマーを殺さない理由

ソースノード: 3083686

In
ChatGPT はプログラマーを殺すことになるでしょうか?
では、プログラマーの仕事を奪う恐れのある多くの需要抑制要因を調査しました。また、プログラマーの需要を高めることでカウンターウェイトとして機能する DEMAND STIMULANTS についても触れました。

この投稿では、について詳しく説明します 需要刺激剤.

新しいコンピューティング パラダイムと市場を構成する需要刺激剤は、コーディングの仕事の減少を阻止するだけでなく、コーディング者の数を増加させます。

新しいコンピューティングパラダイム

Anyone who has followed the IT industry for the last two decades or longer would have observed many waves of computing paradigms like Web, Mobile, Social, Cloud, and Blockchain alongside the growth of ERP, RAD, AI, and other demand suppressors described
前回の投稿で.

コンピューティング パラダイムの新たな波が起こるたびに、プログラマーに対する新たな需要が生まれました。

  • Web: クライアント/サーバー アーキテクチャ ベースの ERP のかなりの部分を、サプライヤー、顧客、その他の利害関係者とのインターネット ベースの取引をサポートするために拡張する必要がありました。
  • モバイル: CRM などの既存のアプリケーションの多くは「モバイル化」 (または、お好みで「モバイル化」) する必要がありました。
  • クラウド: オンプレミス アプリケーションは、AWS、Azure、Oracle Cloud Infrastructure などのハイパースケーラー クラウドに移行する必要がありました。

Gen AI is the latest wave. By automating coding to some extent, it will suppress demand for coders. However, by requiring training of AI on industry- and enterprise-specific data – “last mile training” as Oracle calls it – Gen AI will also stimulate demand
for coders.

新しい市場

何十年にもわたって、私たちはソフトウェア製品会社や SAAS 会社が急増し、デジタル変革や消費者向けテクノロジーの波が押し寄せるのを見てきました。

彼らは、次のようなコーディングの仕事に新しい市場を生み出しました。

  • COTS (Commercial Off The Sheet) 企業および SAAS 企業のエンジニアリング組織
  • オープンソース ソフトウェアや WordPress プラグインなどのツール (RAD / ローコード) ベンダー。
  • Gen AI プラットフォーム開発者
  • Big4他コンサルティング会社のDX実践
  • フィンテック、フードデリバリー、ライドシェア、ルームシェア、旅行、その他の業界における消費者向けインターネットのスタートアップ。
  • Software Is The Brand companies. Coined by Forrester, the term SITB refers to the practice among banking, engineering and other non-software industries to differentiate themselves via software. Examples of SITB include Trade Finance and High Value Fund
    Transfer software in banks, and Internet of Things (IoT) in manufacturing automation companies.

----

@マットターク: Whatever happened to the Internet of Things? 10 years ago, IoT was the next big thing. Tons of new startups, VC money and hype. Ended
up producing just *one* currently independent public company today, Samsara.

@s_ketharaman: It could be argued that IoT has been in use in chemical process plants etc. for 40+ years in the form of sensors, DCS, and PLCs.
At most, these products will need to be upgraded to ZigBee and other open Internet protocols to make them true IoT. But those opportunities will likely be tapped by Honeywell, Schneider and other existing process control equipment suppliers and may not create
opportunities for new startups.

----

  • ソフトウェア企業以外の製品への AI の導入。例えば シーメンスの産業用副操縦士.

----

Microsoft と Siemens は、保守スタッフの修理を支援する Siemens Industrial Copilot と呼ばれる製造アシスタントを開発しました。 – @スーパーグレーズ。

-------

If recent history is any guide, I predict that Gen AI will create more coding jobs. At most, it might lead to a displacement of jobs from engineering to professional services organizations (PSO). (For the uninitiated, coders who develop the core product
on the roadmap of a COTS or SAAS company are in the engineering org, and coders who implement or support the product for a specific customer of such a company or its implementation partners are in the professional services org.)

That said, we must recognize one major difference between Generative AI and the demand suppressors that came before it: ERP, RAD / Low Code etc. obviated the need for code. They did not produce what coders produced. Whereas Gen AI does not obviate the need
for code. It produces what coders would otherwise have produced.

----

@vkhosla: Fun story – at a recent coding hackathon, the winner was a marketer. Not a coder, but a marketer. Previously it was the best coder who
won, less dependent on idea and more on execution and ability to jerry rig a solution. Now it’s the best idea that wins since we’ve democratized what it means to program and barriers to entry are much lower (i.e. natural language!)

----

その点で、Gen AI は、過去の需要抑制要素とは異なり、プログラマー、デザイナー、アーキテクトに対して直接競争する姿勢を持っています。

したがって、上で議論した新しいコンピューティング パラダイムと市場によって促進されるコーダーに対する新たな需要は、ChatGPT によっても満たされる可能性があると主張できます。

ChatGPT を使用して既製のコードを取得した私の個人的な経験から言えば、Gen AI によって、プレーンな HTML CSS コーディング スキルに対する需要は確実に減少します。

複雑な Web サイトやアプリケーションに移ります。次の例を見てみましょう。

---- 

Me: Uber クローンのコード?
AI言語モデルを活用してコードのデバッグからデータの異常検出まで、: Creating a full Uber clone is a complex and extensive project that involves multiple components, including mobile apps for passengers and drivers, a backend server, payment processing, mapping and navigation integration, and more.
It’s a project that would typically require a team of developers and significant resources. I can provide you with a high-level overview of the components you would need and some sample code snippets to get you started, but keep in mind that building a full
Uber clone is beyond the scope of a simple code snippet…

----

完全な応答を見ることができます
こちら
。 ChatGPT は、Uber Clone アプリの多くの構成要素のコード スニペットを提供しましたが、上記の抜粋から、高度な Web サイトやアプリケーションを構築するにはコーダーが依然として必要であることは明らかです。

プログラマーができることは、Gen AI パーソナル アシスタントを使用して、より高品質のコードをより速く書くことです。この能力において、Gen AI はミッドレンジおよびシニアレベルのプログラマーを置き換えるのではなく、補完します。 Gartner は、これに関連してプロによるヒントをいくつか提供しています。

  • AI 支援ソフトウェア エンジニアリングにより、開発者の生産性が向上し、開発チームがビジネスを運営するためのソフトウェアに対する需要の増大に対処できるようになります。
  • AI を組み込んだ開発ツールにより、ソフトウェア エンジニアはコードの作成に費やす時間が短縮され、魅力的なビジネス アプリケーションの設計や構成など、より高いレベルの活動に集中することが容易になります。

私はそれを使用する機会がありませんでしたが、Microsoft Github Copilot コーディング アシスタントについて良い評判を聞きました。

他のすべてがうまくいかない場合は、軽い気持ちで、シリコンバレーの古い格言を思い出してください。

うまく経営されているテクノロジー企業は 2 倍の人員過剰です。経営状態の悪いハイテク企業は 4 倍の人員過剰です。

プログラマーにとって、それ以上に雇用の安定を保証する必要はありません。

-------

需要を刺激するものを作るのは自分たちのスキルセットを超えているというプログラマーの不満の声が聞こえます。

They’re right. Like before, product managers and marketers aka normies will create the new computing paradigms and markets sparking greater demand for coders in the age of Gen AI. However, they will need to be supported by coders, designers and architects
aka geeks in this endeavor.

Ergo Generative AI は、オタクが一般の人々と協力するユニークな機会を提供します。

開示: オラクルは元雇用主です。

タイムスタンプ:

より多くの フィンテクトラ