265SmithWatt 75Neumann 55.YunusAbed , AI20s.com JHDHFL 20
will korea help unite humans and deep learning ai
Koreaa was second in king charels ai wor;d series
korea has always invested a lot in ai
korea days are one of 4 national tongue features at nvidia annual summits
but is korea going to be too late in 2025
lasy weels csis korea in 2025 barely mentioned ai
lets hopw next weeks kennan center wilso horea afternoon does beter - its comnvemnor recentl;y wrote thios
Since the debut of ChatGPT in late 2022, generative AI has been viewed as a key component for economic growth and technological development. How best to integrate this new technology, however, is the key challenge faced by companies and countries alike.
Despite the hype behind AI, companies have yet to fully adopt generative AI. With any new technology, it takes time for companies to implement and best utilize the technology. However, generative AI comes with additional challenges. It has a tendency to “hallucinate,” meaning to make up data, raising questions about its reliability. In a New York legal case, for example, AI created a fictional legal precedent in the brief it generated.
For a country like Korea, the challenge could be even more difficult. The large language models that underpin generative AI models such as ChatGPT require enormous amounts of data to train. While ChatGPT has used publicly available data on the internet, it and other leading AI companies have also worked to integrate proprietary data into their models. It is unclear whether Kakao or Naver can compete with Google, Meta or Microsoft, which supports ChatGPT, in a competition for data.
It is also unclear if building ever-larger large language models is a viable path forward for AI. The world’s most advanced generative AI models have already absorbed much of the world’s available data. Firms are now increasingly turning to synthetic data — data created by AI itself — to fill the data gap. However, a recent study in Nature found that because of the compounding of errors from using synthetic data, AI systems risk collapsing if trained on increasingly larger amounts of synthetic data. Without a new technological breakthrough, generative AI based on large language models will face limits on its development.
On a more basic level, companies face a cost-benefit calculation. Generative AI is generally presented as a way to address a wide range of tasks. However, as Erik Hoel, an American neuroscientist, has pointed out, because large language models need immense amounts of data to train, they are best at skills where data is plentiful. These also tend to be low value-added areas. From a corporate perspective does it make sense to replace low-wage workers with higher-cost technology for skills that are widely available? This suggests for generative AI to be successful it needs to begin providing higher-value skills or improve the productivity of workers in higher-level tasks. This basic challenge could provide Korean firms and Korea more broadly a path forward for integrating AI into the economy.
Rather than viewing generative AI as a means to replace workers, a better approach is asking how AI can help workers become more productive and avoid the hallucination and potential collapse issues related to large language models. This involves focusing on more specialized models.
Specialized AI models tend to have lower levels of hallucinations. The data used to train the models is higher quality and often possesses fewer errors than consuming publicly available data on the internet.
Google’s DeepMind provides an example of how specialized models can produce higher value data. Last year, it discovered 2.2 million potential new crystalline structures, of which 380,000 are considered the most stable. By traditional methods, this would have taken 800 years. These new crystalline structures could provide breakthroughs to improve semiconductors or EV batteries. This approach would also help Korean firms maintain a competitive edge in these industries. More broadly utilizing AI to improve or develop new products would enhance productivity in ways that would justify significant investments in AI.
Korea’s own demographic challenges may also give it an advantage in developing advanced AI models. One promising area for developing AI is robotics. Because robots learn from their interaction with the real world, they produce their own data for learning and have fewer limits on consumable data. They are only constrained by their interactions.
Declining birthrates have pushed Korean firms to integrate more industrial robots into production. Integrating AI with industrial robots could provide Korea with a way to develop high-value advanced AI, but also aid in improving the productivity of small and medium-sized firms (SMEs). Based on data from 2019, SMEs are only 32 percent as productive as large firms in Korea. Boosting productivity in SMEs would significantly improve Korea’s overall economy.
Korea already plays an important role in the advancement of AI due to the development of high-bandwidth memory. Without these chips, Nvidia’s graphics processors would not be able to power AI models to the degree they have. However, for Korea to move beyond being a hardware partner for AI and to integrate the technology more broadly into its economy, it will need a different approach focused on specialized models for research and development, along with integration into robotics.
Troy Stangarone is the director of the Hyundai Motor-Korea Foundation Center for Korean History and Public Policy and the deputy director of the Indo-Pacific Program at the Woodrow Wilson Center.
i welcome mai8l chris.macrae@yahoo.co.uk FC regions 2025report.com ai20s.com www.economistdiary.com www.ecopnomistjapan.com asia rising since 1962 - von neumann quizzes since 1951
chris macrae
clear;lyt the 6 hopur coup in South Korea is aa setback to Korea playing a defini9ng role for humanity- yet the brainpower in Korea is huge and will likley contribute to some of the best transtaional ai
its notable that s korea is a world leader in engineering other chose not to focus on
nuclear acccording to US CSIS now vital to closing us energy gaps
shipbuilding - 80% of world trade is sheipped- and remains the ecological core of trade
according to gemini today these are areas of AI that Koprea is a world leader in
To find more specific information, you can:
I asked gemini about expectations on korea leading on data soveregnty and agency
However, challenges remain:
In conclusion:
South Korea has the potential to be a leader in data sovereignty and AI agency. By leveraging its technological strengths, fostering a strong AI ecosystem, and implementing effective data protection policies, Korea can position itself as a global leader in the responsible development and use of AI.
South Korea is emerging as a significant player in the development of autonomous AI, particularly in the areas of:
However, it's important to note that:
Overall:
While South Korea may not yet be considered a "leader" in all aspects of autonomous AI, it is a strong contender with significant potential. Its strengths in technology, government support, and a thriving AI ecosystem position it well for future advancements in this field.
oth Korea and Taiwan possess strong AI capabilities, making them potential partners in AI education, particularly at the K-12 level.
Strengths of Korea:
Strengths of Taiwan:
Potential for Partnership:
Reasons for Partnership:
Potential Challenges:
Overall:
Despite potential challenges, a strong partnership between Korea and Taiwan in AI education and research holds significant promise. By leveraging their respective strengths and addressing potential concerns, both countries can benefit from increased collaboration and contribute significantly to the advancement of AI globally.
Dec 13, 2024