报告-生成式AI_像ChatGPT这样的工具如何改变你的企业.pdf
5墨值下载
Generative AI is here:
How tools like ChatGPT
could change your business
Generative AI and other foundation models are changing the AI game, taking
assistive technology to a new level, reducing application development time,
and bringing powerful capabilities to nontechnical users.
December 2022
© Getty Images
by Michael Chui, Roger Roberts, and Lareina Yee
In the spirit of this article’s topic, we asked
ChatGPT—a generative AI language model that
can create original content in response to a user
prompt—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.
Products like ChatGPT and GitHub Copilot, as
well as the underlying AI models that power such
systems (Stable Diffusion, DALL·E 2, GPT3, 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.
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,
GPT3.5, 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.
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
2
of 5
5墨值下载
【版权声明】本文为墨天轮用户原创内容，转载时必须标注文档的来源（墨天轮），文档链接，文档作者等基本信息，否则作者和墨天轮有权追究责任。如果您发现墨天轮中有涉嫌抄袭或者侵权的内容，欢迎发送邮件至：contact@modb.pro进行举报，并提供相关证据，一经查实，墨天轮将立刻删除相关内容。
下载排行榜
评论