전체 글
반응형
[ChatGPT News 스크립트] 맥킨지 자료, ChatGPT로 인한 업무 변화
2023. 6. 29. 17:24ㆍChatGPT/ChatGPT News 스크립트
맥킨지에서 나온 자료로, ChatGPT로 인하여 어떻게 업무 변화되는지 자세히 기술되어 있다.
산업혁명에 있어 독창성의 발전과, 업무적 활용방법도 나와있어
자세한 설명을 얻을 수 있다.
—how it would set the context. Our prompt to the system:
Write the opening paragraph for an article about how transformative generative AI will be for business,
in the style of McKinsey & Company.
—ChatGPT’s response:
The rise of generative AI has the potential to be a major game-changer for businesses. This technology, which allows for the creation of original content by learning from existing data, has the power to revolutionize industries and transform the way companies operate. By enabling the automation of many tasks that were previously done by humans, generative AI has the potential to increase efficiency and productivity, reduce costs, and open up new opportunities for growth. As such, businesses that are able to effectively leverage the technology are likely to gain a significant competitive advantage.
—Not perfect but overwhelmingly impressive.
For us and many executives we’ve spoken to recently, entering one prompt into ChatGPT, developed by OpenAI, was all it took to see the power of generative AI. In the first five days of its release, more than a million users logged into the platform to experience it for themselves. OpenAI’s servers can barely keep up with demand, regularly flashing a message that users need to return later when server capacity frees up.
—With generative AI, computers can now arguably exhibit creativity.
We strive to provide individuals with disabilities equal access to our website. If you would like information about this content we will be happy to work with you. Please email us at: McKinsey_Website_Accessibility@mckinsey.com
Products like ChatGPT and GitHub Copilot, as well as the underlying AI models that power such systems (Stable Diffusion, DALL·E 2, GPT - 3, to name a few), are taking technology into realms once thought to be reserved for humans. With generative AI, computers can now arguably exhibit creativity. They can produce original content in response to queries, drawing from data they’ve ingested and interactions with users. They can develop blogs, sketch package designs, write computer code, or even theorize on the reason for a production error.
But as with every new technology, business leaders must proceed with eyes wide open, because the technology today presents many ethical and practical challenges.
This latest class of generative AI systems has emerged from foundation models—large-scale, deep learning models trained on massive, broad, unstructured data sets (such as text and images) that cover many topics. Developers can adapt the models for a wide range of use cases, with little fine-tuning required for each task. For example, GPT - 3.5, the foundation model underlying ChatGPT, has also been used to translate text, and scientists used an earlier version of GPT to create novel protein sequences. In this way, the power of these capabilities is accessible to all, including developers who lack specialized machine learning skills and, in some cases, people with no technical background. Using foundation models can also reduce the time for developing new AI applications to a level rarely possible before.
Generative AI promises to make 2023 one of the most exciting years yet for AI. But as with every new technology, business leaders must proceed with eyes wide open, because the technology today presents many ethical and practical challenges.
Moving illustration of wavy blue lines that was produced using computer code.
Pushing further into human realms
More than a decade ago, we wrote an article in which we sorted economic activity into three buckets—production, transactions, and interactions—and examined the extent to which technology had made inroads into each. Machines and factory technologies transformed production by augmenting and automating human labor during the Industrial Revolution more than 100 years ago, and AI has further amped up efficiencies on the manufacturing floor. Transactions have undergone many technological iterations over approximately the same time frame, including most recently digitization and, frequently, automation.
Until recently, interaction labor, such as customer service, has experienced the least mature technological interventions. Generative AI is set to change that by undertaking interaction labor in a way that approximates human behavior closely and, in some cases, imperceptibly. That’s not to say these tools are intended to work without human input and intervention. In many cases, they are most powerful in combination with humans, augmenting their capabilities and enabling them to get work done faster and better.
Generative AI is also pushing technology into a realm thought to be unique to the human mind: creativity. The technology leverages its inputs (the data it has ingested and a user prompt) and experiences (interactions with users that help it “learn” new information and what’s correct/incorrect) to generate entirely new content. While dinner table debates will rage for the foreseeable future on whether this truly equates to creativity, most would likely agree that these tools stand to unleash more creativity into the world by prompting humans with starter ideas.
These models are in the early days of scaling, but we’ve started seeing the first batch of applications across functions, including the following (exhibit):
The awe-inspiring results of generative AI might make it seem like a ready-set-go technology, but that’s not the case. Its nascency requires executives to proceed with an abundance of caution. Technologists are still working out the kinks, and plenty of practical and ethical issues remain open. Here are just a few:
Like humans, generative AI can be wrong. ChatGPT, for example, sometimes “hallucinates,” meaning it confidently generates entirely inaccurate information in response to a user question and has no built-in mechanism to signal this to the user or challenge the result. For example, we have observed instances when the tool was asked to create a short bio and it generated several incorrect facts for the person, such as listing the wrong educational institution.
Filters are not yet effective enough to catch inappropriate content. Users of an image-generating application that can create avatars from a person’s photo received avatar options from the system that portrayed them nude, even though they had input appropriate photos of themselves.
Systemic biases still need to be addressed. These systems draw from massive amounts of data that might include unwanted biases.
Individual company norms and values aren’t reflected. Companies will need to adapt the technology to incorporate their culture and values, an exercise that requires technical expertise and computing power beyond what some companies may have ready access to.
Intellectual-property questions are up for debate. When a generative AI model brings forward a new product design or idea based on a user prompt, who can lay claim to it? What happens when it plagiarizes a source based on its training data?
In companies considering generative AI, executives will want to quickly identify the parts of their business where the technology could have the most immediate impact and implement a mechanism to monitor it, given that it is expected to evolve quickly. A no-regrets move is to assemble a cross-functional team, including data science practitioners, legal experts, and functional business leaders, to think through basic questions, such as these:
Meanwhile, it’s essential to encourage thoughtful innovation across the organization, standing up guardrails along with sandboxed environments for experimentation, many of which are readily available via the cloud, with more likely on the horizon.
—how it would set the context. Our prompt to the system:
Write the opening paragraph for an article about how transformative generative AI will be for business,
in the style of McKinsey & Company.
—ChatGPT’s response:
The rise of generative AI has the potential to be a major game-changer for businesses. This technology, which allows for the creation of original content by learning from existing data, has the power to revolutionize industries and transform the way companies operate. By enabling the automation of many tasks that were previously done by humans, generative AI has the potential to increase efficiency and productivity, reduce costs, and open up new opportunities for growth. As such, businesses that are able to effectively leverage the technology are likely to gain a significant competitive advantage.
—Not perfect but overwhelmingly impressive.
For us and many executives we’ve spoken to recently, entering one prompt into ChatGPT, developed by OpenAI, was all it took to see the power of generative AI. In the first five days of its release, more than a million users logged into the platform to experience it for themselves. OpenAI’s servers can barely keep up with demand, regularly flashing a message that users need to return later when server capacity frees up.
—With generative AI, computers can now arguably exhibit creativity.
We strive to provide individuals with disabilities equal access to our website. If you would like information about this content we will be happy to work with you. Please email us at: McKinsey_Website_Accessibility@mckinsey.com
Products like ChatGPT and GitHub Copilot, as well as the underlying AI models that power such systems (Stable Diffusion, DALL·E 2, GPT - 3, to name a few), are taking technology into realms once thought to be reserved for humans. With generative AI, computers can now arguably exhibit creativity. They can produce original content in response to queries, drawing from data they’ve ingested and interactions with users. They can develop blogs, sketch package designs, write computer code, or even theorize on the reason for a production error.
But as with every new technology, business leaders must proceed with eyes wide open, because the technology today presents many ethical and practical challenges.
This latest class of generative AI systems has emerged from foundation models—large-scale, deep learning models trained on massive, broad, unstructured data sets (such as text and images) that cover many topics. Developers can adapt the models for a wide range of use cases, with little fine-tuning required for each task. For example, GPT - 3.5, the foundation model underlying ChatGPT, has also been used to translate text, and scientists used an earlier version of GPT to create novel protein sequences. In this way, the power of these capabilities is accessible to all, including developers who lack specialized machine learning skills and, in some cases, people with no technical background. Using foundation models can also reduce the time for developing new AI applications to a level rarely possible before.
Generative AI promises to make 2023 one of the most exciting years yet for AI. But as with every new technology, business leaders must proceed with eyes wide open, because the technology today presents many ethical and practical challenges.
Moving illustration of wavy blue lines that was produced using computer code.
—시스템에 대한 우리의 프롬프트 :
McKinsey & Company의 스타일로
혁신적인 생성 AI가 비즈니스에 어떻게 도움이 될 것인지에 대한 기사의 시작 단락을 작성하십시오.
—ChatGPT의 응답:
생성형 AI의 부상은 기업의 주요 게임 체인저가 될 가능성이 있습니다.
기존 데이터에서 학습하여 독창적인 콘텐츠를 만들 수 있는 이 기술은 산업에 혁명을 일으키고
기업 운영 방식을 변화시킬 수 있는 힘을 가지고 있습니다.
생성 AI는 이전에 인간이 수행했던 많은 작업의 자동화를 가능하게 함으로써 효율성과 생산성을 높이고 비용을 절감하며 새로운 성장 기회를 열 수 있는 잠재력을 가지고 있습니다. 따라서 기술을 효과적으로 활용할 수 있는 기업은 상당한 경쟁 우위를 확보할 수 있습니다.
—Not perfect but overwhelmingly impressive. (완벽하지는 않지만 강한 인상을 남깁니다.)
For us and many executives we’ve spoken to recently, entering one prompt into ChatGPT, developed by OpenAI, was all it took to see the power of generative AI. In the first five days of its release, more than a million users logged into the platform to experience it for themselves. OpenAI’s servers can barely keep up with demand, regularly flashing a message that users need to return later when server capacity frees up.
우리와 최근에 이야기를 나눈 많은 경영진에게 OpenAI에서 개발한 ChatGPT에 프롬프트 하나를 입력하는 것만으로도 생성 AI의 힘을 볼 수 있었습니다. 출시 5일 동안 백만 명이 넘는 사용자가 플랫폼에 로그인하여 직접 경험했습니다. OpenAI의 서버는 수요를 간신히 따라갈 수 있으며 서버 용량이 확보되면 사용자가 나중에 반환해야 한다는 메시지를 정기적으로 주의를 주고 있습니다.
하지만, 서버는 수요에 비하여 주의가 많이 필요하며, 서버 용량 또한 언제 터질지 모르는 사태에 직면해 있다는 것을 말하고 있습니다.
우리나라 사람들 중, 사용하지 않는 사람들을 찾아보기 힘든 카카오도 마찬가지죠.
사용자가 너무 많으면 서버를 구동하기 힘든 상황이 나타남을 말해주고 있습니다.
—With generative AI, computers can now arguably exhibit creativity. ( 생성 AI를 통한 창의성 )
We strive to provide individuals with disabilities equal access to our website. If you would like information about this content we will be happy to work with you. Please email us at: McKinsey_Website_Accessibility@mckinsey.com
Products like ChatGPT and GitHub Copilot, as well as the underlying AI models that power such systems (Stable Diffusion, DALL·E 2, GPT - 3, to name a few), are taking technology into realms once thought to be reserved for humans. With generative AI, computers can now arguably exhibit creativity. They can produce original content in response to queries, drawing from data they’ve ingested and interactions with users. They can develop blogs, sketch package designs, write computer code, or even theorize on the reason for a production error.
ChatGPT 및 GitHub Copilot과 같은 제품과 이러한 시스템을 구동하는 기본 AI 모델(Stable Diffusion, DALL· E 2, GPT-3)는 한때 인간을 위해 예약되어 있다고 생각되었던 영역으로 기술을 도입하고 있습니다. 생성 AI를 통해 컴퓨터는 이제 틀림없이 창의성을 발휘할 수 있습니다. 쿼리에 대한 응답으로 원본 콘텐츠를 생성할 수 있으며, 수집한 데이터 및 사용자와의 상호 작용에서 가져올 수 있습니다. 블로그를 개발하고, 패키지 디자인을 스케치하고, 컴퓨터 코드를 작성하거나, 생산 오류의 원인에 대한 이론을 세울 수도 있습니다.
블로그 글부터 시작해서, 패키지 디자인, 코딩 등 다양한 정보들을 쉽게 알 수 있습니다.
거기에 독창성까지 있다니, 안할 이유가 없습니다.
But as with every new technology, business leaders must proceed with eyes wide open, because the technology today presents many ethical and practical challenges. (그러나 모든 신기술과 마찬가지로 비즈니스 리더는 윤리적, 실제적 과제를 위해 눈을 크게 뜨고 진행해야 합니다.)
This latest class of generative AI systems has emerged from foundation models—large-scale, deep learning models trained on massive, broad, unstructured data sets (such as text and images) that cover many topics. Developers can adapt the models for a wide range of use cases, with little fine-tuning required for each task. For example, GPT - 3.5, the foundation model underlying ChatGPT, has also been used to translate text, and scientists used an earlier version of GPT to create novel protein sequences. In this way, the power of these capabilities is accessible to all, including developers who lack specialized machine learning skills and, in some cases, people with no technical background. Using foundation models can also reduce the time for developing new AI applications to a level rarely possible before.
Generative AI promises to make 2023 one of the most exciting years yet for AI. But as with every new technology, business leaders must proceed with eyes wide open, because the technology today presents many ethical and practical challenges.
이 최신 종류의 생성형 AI 시스템은 많은 주제를 다루는 방대하고 광범위하며 구조화되지 않은 데이터 세트(예: 텍스트 및 이미지)에 대해 훈련된 대규모 딥 러닝 모델인 기초 모델에서 등장했습니다. 개발자는 다양한 사용 사례에 맞게 모델을 조정할 수 있으며 각 작업에 대한 미세 조정이 거의 필요하지 않습니다. 예를 들어, ChatGPT의 기본 모델인 GPT-3.5도 텍스트 번역에 사용되었으며 과학자들은 이전 버전의 GPT를 사용하여 새로운 단백질 서열을 만들었습니다. 이러한 방식으로 이러한 기능의 힘은 전문 기계 학습 기술이 부족한 개발자와 경우에 따라 기술적 배경이 없는 사람을 포함하여 모든 사람이 액세스할 수 있습니다. 또한 파운데이션 모델을 사용하면 새로운 AI 애플리케이션을 개발하는 데 걸리는 시간을 이전에는 거의 불가능했던 수준으로 단축할 수 있습니다.
생성형 AI는 2023년을 AI 분야에서 가장 흥미로운 해 중 하나로 만들 것을 약속합니다. 그러나 모든 신기술과 마찬가지로 비즈니스 리더는 오늘날 기술이 많은 윤리적, 실제적 과제를 제시하기 때문에 눈을 크게 뜨고 진행해야 합니다
Pushing further into human realms(인간 영역으로 더 나아가기)
More than a decade ago, we wrote an article in which we sorted economic activity into three buckets—production, transactions, and interactions—and examined the extent to which technology had made inroads into each. Machines and factory technologies transformed production by augmenting and automating human labor during the Industrial Revolution more than 100 years ago, and AI has further amped up efficiencies on the manufacturing floor. Transactions have undergone many technological iterations over approximately the same time frame, including most recently digitization and, frequently, automation.
Until recently, interaction labor, such as customer service, has experienced the least mature technological interventions. Generative AI is set to change that by undertaking interaction labor in a way that approximates human behavior closely and, in some cases, imperceptibly. That’s not to say these tools are intended to work without human input and intervention. In many cases, they are most powerful in combination with humans, augmenting their capabilities and enabling them to get work done faster and better.
Generative AI is also pushing technology into a realm thought to be unique to the human mind: creativity. The technology leverages its inputs (the data it has ingested and a user prompt) and experiences (interactions with users that help it “learn” new information and what’s correct/incorrect) to generate entirely new content. While dinner table debates will rage for the foreseeable future on whether this truly equates to creativity, most would likely agree that these tools stand to unleash more creativity into the world by prompting humans with starter ideas.
100여 년 전, 우리는 경제 활동을 생산, 거래, 상호 작용이라는 세 가지 버킷으로 분류하고 기술이 각각에 침투한 정도를 조사한 기사를 썼습니다. 기계와 공장 기술은 100여 년 전 산업 혁명 기간 동안 인간의 노동력을 늘리고 자동화하여 생산을 변화시켰고, AI는 제조 현장의 효율성을 더욱 높였습니다. 거래는 가장 최근의 디지털화 및 자동화를 포함하여 거의 동일한 기간 동안 많은 기술 반복을 거쳤습니다.
최근까지 고객 서비스와 같은 상호 작용 노동은 가장 성숙하지 않은 기술 개입을 경험했습니다. 생성 AI는 인간의 행동에 밀접하고 경우에 따라 눈에 띄지 않는 방식으로 상호 작용 노동을 수행함으로써 이를 변화시킬 예정입니다. 그렇다고 해서 이러한 도구가 사람의 입력과 개입 없이 작동하도록 의도된 것은 아닙니다. 많은 경우, 그들은 인간과 함께 가장 강력하여 능력을 강화하고 작업을 더 빠르고 더 잘 수행할 수 있도록 합니다.
생성형 AI는 또한 인간의 마음에 고유하다고 생각되는 영역인 창의성으로 기술을 밀어붙이고 있습니다. 이 기술은 입력(수집한 데이터 및 사용자 프롬프트)과 경험(새로운 정보와 옳고 그른 것을 "학습"하는 데 도움이 되는 사용자와의 상호 작용)을 활용하여 완전히 새로운 콘텐츠를 생성합니다. 이것이 진정으로 창의성과 동일한지 여부에 대한 저녁 식탁 논쟁은 가까운 장래에 격렬해질 것이지만, 대부분의 사람들은 이러한 도구가 인간에게 시작 아이디어를 촉구함으로써 세상에 더 많은 창의성을 발휘할 수 있다는 데 동의할 것입니다.
→ 필자는 얘기하고 있습니다. 기존의 산업혁명과 완전 다르다는 것을요. 디지털화 및 자동화를 포함하여 거의 동일한 기간 동안 많은 기술 반복을 거쳤고, 그러한 과정을 통해 혁명적인 발전을 하는 시대를 나누어 1차, 2차, 3차 산업혁명으로 불리고 있습니다.
하지만, 독창성이 있다면 기존 같은 동작만의 반복으로 산업적인 부분만 강조되었던 시대와는 완전 다른 흐름이 되지 않을까 생각합니다.
독창성의 정도를 따로 보아, 정보화 혁명으로 재분류되어야 하지 않을까요?
충분히 그럴만한 가치가 있다고 생각합니다.
These models are in the early days of scaling, but we’ve started seeing the first batch of applications across functions, including the following (exhibit):
아직 확장 초기 단계이지만 다음을 포함하여 함수 전반에 걸쳐 응용 프로그램의 첫 번째 예시를 보기 시작했습니다(전시).
(아래는 위에 대한 내용을 표로 정리한 것입니다. )
→ 위 표에서 나온 것과 같이
In companies considering generative AI, executives will want to quickly identify the parts of their business where the technology could have the most immediate impact and implement a mechanism to monitor it, given that it is expected to evolve quickly. A no-regrets move is to assemble a cross-functional team, including data science practitioners, legal experts, and functional business leaders, to think through basic questions, such as these:
생성형 AI를 고려하는 기업에서 경영진은 기술이 가장 즉각적인 영향을 미칠 수 있는 비즈니스 부분을 신속하게 식별하고 빠르게 발전할 것으로 예상된다는 점을 감안할 때 이를 모니터링하는 메커니즘을 구현하기를 원할 것입니다. 후회하지 않는 조치는 데이터 과학 실무자, 법률 전문가 및 기능적 비즈니스 리더를 포함한 교차 기능 팀을 구성하여 다음과 같은 기본적인 질문을 생각하는 것입니다.
Meanwhile, it’s essential to encourage thoughtful innovation across the organization, standing up guardrails along with sandboxed environments for experimentation, many of which are readily available via the cloud, with more likely on the horizon.
한편, 조직 전반에 걸쳐 사려 깊은 혁신을 장려하는 것이 필수적이며, 실험을 위한 샌드박스 환경과 함께 가드레일을 세우는 것이 중요하며, 그 중 다수는 클라우드를 통해 쉽게 사용할 수 있으며 더 많은 가능성이 있습니다.
→ 결국 인류의 발전을 위해서는 독창성과 효율성을 동시에 가진 인공지능의 사용은 불가피할 것으로 보이며,
이미 많은 업체에서 시작을 하고 있다.
하지만 지금은 첫 걸음마에 불과해서 끊임없는 위험성에 대한 연구가 필요하다.
이러한 가이드라인을 끊임없이 만들고 연구하는 것이 우리의 과제이자 숙명이라고 생각한다.
.
출처 : By Michael Chui, Roger Roberts, and Lareina Yee
How generative AI & ChatGPT will change business | McKinsey
Generative AI is here: How tools like ChatGPT could change your business
In this article, we look at how ChatGPT and other generative AI tools are reshaping the business world and bringing powerful capabilities to nontechnical users.
www.mckinsey.com
| [ChatGPT News 스크립트]AI 규제 법안(유럽, 미국 NMA)과 AI의 독창성 (0) | 2023.06.30 |
|---|---|
| [ChatGPT News 스크립트]ChatGPT 경쟁사-Anthropic사의 클로드Claude (0) | 2023.06.29 |
| [ChatGPT News 스크립트]OpenAI, ChatGPT Professional실험단계 (0) | 2023.06.28 |
| [ChatGPT News 스크립트]Microsoft사의 OpenAI 도입 (0) | 2023.06.27 |
| [ChatGPT News 스크립트] "AI챗봇 챗GPT 개발사, 기업가치 36.8조에 지분매각 협상" (0) | 2023.06.27 |