“SK Wonderland at CES 2024;” SK Group Chairman: AI-led revolution poses challenges to companies

On Tuesday at CES 2024, SK Group [1.] displayed world-leading Artificial Intelligence (AI) and carbon reduction technologies under an amusement park concept called “SK Wonderland.”   It provided CES attendees a view of a world that uses the latest AI and clean technologies from SK companies and their business partners to a create a smarter, greener world. Highlights of the booth included:

  • Magic Carpet Ride in a flying vehicle embedded with an AI processor that helps it navigate dense, urban areas – reducing pollution, congestion and commuting frustrations
  • AI Fortune Teller powered by next-generation memory technologies that can help computers analyze and learn from massive amounts of data to predict the future
  • Dancing Car that’s fully electric, able to recharge in 20 minutes or less and built to travel hundreds of miles between charges
  • Clean Energy Train that’s capable of being powered by hydrogen, whose only emission is water
  • Rainbow Tube that shows how plastics are finding a new life through a technology that turns waste into fuel

Note 1. SK Group is South Korea’s second-largest conglomerate, with Samsung at number one.

SK’s CES 2024 displays include participation from seven SK companies — SK Inc., SK Innovation, SK Hynix, SK Telecom, SK E&S, SK Ecoplant and SKC. While the displays are futuristic, they’re based on technologies that SK companies and their global partners have already developed and are bringing to market.

SK Group Chairman Chey Tae-won said that companies are facing challenges in navigating the transformative era led by artificial intelligence (AI) due to its unpredictable impact and speed.  He said AI technology and devices with AI are the talk of the town at this year’s annual trade show and companies are showcasing their AI innovations achieved through early investment.

“We are on the starting line of the new era, and no one can predict the impact and speed of the AI revolution across the industries,” Chey told Korean reporters after touring corporate booths on the opening day of CES 2024 at the Las Vegas Convention Center in Las Vegas.  Reflecting on the rapid evolution of AI technologies, he highlighted the breakthrough made by ChatGPT, a language model launched about a year ago, which has significantly influenced how AI is perceived and utilized globally. “Until ChatGPT, no one has thought of how AI would change the world. ChatGPT made a breakthrough, and everybody is trying to ride on the wave.”

SK Group Chairman Chey Tae-won speaks during a brief meeting with Korean media on the sidelines of CES 2024 at the Las Vegas Convention Center in Las Vegas on Jan. 9, 2024

…………………………………………………………………………………………………………………………………………………………………………………………………………………………………………………………

SK Hynix Inc., SK Group’s chipmaking unit, is one of the prominent companies at CES 2024, boasting its high-performance AI chips like high bandwidth memory (HBM). The latest addition is the HBM3E chips, recognized as the world’s best-performing memory product. Mass production of HBM3E is scheduled to begin in the first half of 2024.

SK Telecom Co. is also working on AI, having Sapeon, an AI chip startup under its wing. Chey stressed the importance of integrating AI services and solutions across SK Group’s diverse business sectors, ranging from energy to telecommunications and semiconductors. “It’s crucial for each company to collaborate and present a unified package or solution rather than developing them separately,” Chey said. “But I don’t think it is necessary to set up a new unit for that. I think we should come up with an integrated channel for customers.”

SK Telecom and Deutsche Telekom are jointly developing Large Language Models for generative AI to be used by telecom network providers.

…………………………………………………………………………………………………………………………………………………………………………………………………………………………………………………………

 

References:

https://en.yna.co.kr/view/AEN20240110001900320#

https://eng.sk.com/news/ces-2024-sk-to-showcase-world-class-carbon-reduction-and-ai-technologies

SK Telecom inspects cell towers for safety using drones and AI

SK Telecom and Deutsche Telekom to Jointly Develop Telco-specific Large Language Models (LLMs)

SK Telecom and Thales Trial Post-quantum Cryptography to Enhance Users’ Protection on 5G SA Network

Generative AI Unicorns Rule the Startup Roost; OpenAI in the Spotlight

Introduction:

Despite mounting pressure on venture capital in a difficult economic environment, money is still flowing into generative Artificial Intelligence (AI) startups.  Indeed, AI startups have emerged as a bright spot for VC investments this year amid a wider slowdown in funding caused by rising interest rates, a slowing economy and high inflation.

VCs have already poured $10.7 billion into Generative AI [1.] start-ups within the first three months of this year, a thirteen-fold increase from a year earlier, according to PitchBook, which tracks start-ups.

Note 1. Generative AI is a type of artificial intelligence that can create new content, such as text, synthetic data, images, and audio.  The recent buzz around Generative AI has been driven by the simplicity of new user interfaces for creating high-quality content in a matter of seconds.

….………………………………………………………………………………….

Tech giants have poured effort and billions of dollars into what they say is a transformative technology, even amid rising concerns about A.I.’s role in spreading misinformation, killing jobs and one day matching human intelligence.  What they don’t publicize is that the results (especially from ChatGPT) may be incorrect or inconclusive.

We take a close look at Generative AI Unicorns with an emphasis on OpenAI (the creator of ChatGPT) and the competition it will face from Google DeepMind.

Generative AI Unicorns and OpenAI:

AI startups make up half of all new unicorns (startups valued at more than $1B) in 2023, says CBInsights.

At Generative AI firms, startups are reaching $1 billion valuations at lightning speed.  There are currently 13 Generative AI unicorns (see chart below), according to CBInsights which said they attained their unicorn status nearly twice as fast as the average $1 billion startup.

Across the 13 Generative AI unicorns, the average time to reach unicorn status was 3.6 years but for the unicorn club as a whole the average is 7 years — almost twice as long.

OpenAI, the poster child for Generative AI with its Chat GPT app, tops the list with a valuation of almost $30 billion.  Microsoft is the largest investor as it provided OpenAI with a $1 billion investment in 2019 and a $10 billion investment in 2023.  Bloomberg reported that the company recently  closed an investment fund, exceeding expectations with a value that surpasses $175 million.

However, OpenAI may have a formidable competitor in Google DeepMind (more details in DeepMind section below).

….……………………………………………………………………………………………………………………………………………………….

Anthropic is #2 with a valuation of $4.4B. It’s an AI safety and research company based in San Francisco, CA.  The company says they “develop large-scale AI systems so that we can study their safety properties at the technological frontier, where new problems are most likely to arise. We use these insights to create safer, steerable, and more reliable models, and to generate systems that we deploy externally, like Claude (to be used with Slack).”

In Q1-2023, Generative AI companies accounted for three of the entrants to the unicorn club with Anthropic, Adept, and Character.AI all gaining valuations of $1B or above.

New Generative AI Unicorns in May:

Ten companies joined the Crunchbase Unicorn Board in May 2023 — double the count for April 2023. Among them were several AI startups:

  • Toronto-basedCohere, a generative AI large language model developer for enterprises, raised $270 million in its Series C funding. The funding was led by Inovia Capital  valuing the 4-year-old company at $2.2 billion.
  • Generative video AI company Runway, based out of New York, raised a $100 million Series D led by Google. The funding valued the 5-year-old company at $1.5 billion.
  • Synthesia, a UK-based artificial intelligence (AI) startup, has raised about $90 million at a valuation of $1 billion from a funding round led by venture capital firms Accel and Nvidia-owned NVentures.  “While we weren’t actively looking for new investment, Accel and NVIDIA share our vision for transforming traditional video production into a digital workflow,” said Victor Riparbelli, co-founder and CEO of Synthesia.

….…………………………………………………………………………………………………………………………………………………..

Google DeepMind:

Alphabet CEO Sundar Pichai said in a blog post, “we’ve been an AI-first company since 2016, because we see AI as the most significant way to deliver on our mission.”

In April, Alphabet Inc. created “Google DeepMind,” in order to bring together two leading research groups in the AI field: the Brain team from Google Research, and DeepMind (the AI startup Google acquired in 2014). Their collective accomplishments in AI over the last decade span AlphaGo, Transformers, word2vec, WaveNet, AlphaFold, sequence to sequence models, distillation, deep reinforcement learning, and distributed systems and software frameworks like TensorFlow and JAX for expressing, training and deploying large scale Machine Learning (ML) models.

By launching DeepMind as Google’s Generative AI solution, there could be a new battle front opening in quantum computing, machine learning perception, gaming and mobile systems, NLP and human-computer interaction and visualization.

A recent DeepMind paper says the Alphabet unit has extended AI capabilities with faster sorting algorithms to create ordered lists.  Their paper says it shows “how artificial intelligence can go beyond the current state of the art,” because ultimately AlphaDev’s sorts use fewer lines of code for sorting sequences with between three elements and eight elements — for every number of elements except four. And these shorter algorithms “do indeed lead to lower latency,” the paper points out, “as the algorithm length and latency are correlated.”

Their researchers created a program based on DeepMind’s AlphaZero program, which beat the world’s best players in chess and Go. That program trained solely by playing games against itself, getting better and better using a kind of massively automated trial-and-error that eventually determines the most optimal approach.

DeepMind’s researchers modified into a new coding-oriented program called AlphaDev, calling this an important next step. “With AlphaDev, we show how this model can transfer from games to scientific challenges, and from simulations to real-world applications,” they wrote on the DeepMind blog.  The newly-discovered sorting algorithms “contain new sequences of instructions that save a single instruction each time they’re applied. AlphaDev skips over a step to connect items in a way that looks like a mistake, but is actually a shortcut.”

….………………………………………………………………………………………………………………………………………………………..

Conclusions:

While many luminaries, such as Henry Kissinger, Eric Schmidt and Daniel Huttenlocher, have lauded Generative AI as the greatest invention since the printing press, the technology has yet to prove itself worthy of the enormous praise.  Their central thesis, that a computer program could “transform the human cognitive process” in a way tantamount to the Enlightenment, is a huge stretch.

Gary Marcus, a well-known professor and frequent critic of A.I. technology, said that OpenAI hasn’t been transparent about the data its uses to develop its systems. He expressed doubt in CEO Sam Altman’s prediction that new jobs will replace those killed off by A.I.

“We have unprecedented opportunities here but we are also facing a perfect storm of corporate irresponsibility, widespread deployment, lack of adequate regulation and inherent unreliability,” Dr. Marcus said.

The promise and potential of Generative AI will not be realized for many years.  Think of it as a “research work in progress” with many twists and turns along the way.

….………………………………………………………………………………………………………………………………..

References:

https://www.cbinsights.com/research/generative-ai-unicorns-valuations-revenues-headcount/

https://pitchbook.com/news/articles/Amazon-Bedrock-generative-ai-q1-2023-vc-deals

Curmudgeon/Sperandeo:  Impact of Generative AI on Jobs and Workers

Generative AI in telecom; ChatGPT as a manager? ChatGPT vs Google Search

Generative AI could put telecom jobs in jeopardy; compelling AI in telecom use cases

 

 

 

Generative AI in telecom; ChatGPT as a manager? ChatGPT vs Google Search

Generative AI is probably the most hyped technology in the last 60 years [1.].  While the potential and power of microprocessors, Ethernet, WiFi, Internet, 4G, and cloud computing all lived up to or exceeded expectations, generative AI has yet to prove itself worthy of its enormous praise.  Simply put, Generative AI is a type of artificial intelligence that can create new content, such as text, images, and audio.

Note 1.  This author has been observing computer and communications technologies for 57 years.  His first tech job for pay was in the summer of 1966 in Dallas, TX.  He did mathematical simulations of: 1.)  Worst Case Data Load on 3 Large Screen Displays (LSDs)-each 7 ft x 7 ft. and 2.) Efficiency of Manual Rate Aided Radar Tracking.  In the summer of 1967 he helped install and test electronic modules for the central command and control system for the Atlantic Fleet Weapons Range at Roosevelt Roads Naval Air station in Puerto Rico.  While there also did a computer simulation of a real time naval air exercise (battle ships, aircraft carriers, jets, helicopters, drones, etc) and displayed the results on the 3 LSDs.  Skipping over his career in academia, industry and as a volunteer officer/chairman at IEEE ComSoc and IEEE SV Tech History, Alan has overseen the IEEE Techblog for over 14 years (since he was asked to do so in March 2009 by the IEEE ComSoc NA Chairman at that time).

………………………………………………………………………………………………………………………………………………………………………………..

Interest in Generative A.I. has exploded. Tech giants have poured effort and billions of dollars into what they say is a transformative technology, even amid rising concerns about A.I.’s role in spreading misinformation, killing jobs and one day matching human intelligence.

It’s been claimed that Generative AI can be used to optimize telecom networks and make them more efficient. This can lead to faster speeds, better reliability, and lower costs.  Another way that generative AI is changing telecommunications is by improving customer service. Generative AI can be used to create virtual assistants that can answer customer questions and provide support. This can free up human customer service representatives to focus on more complex issues.

Generative AI is also being used to improve network security. Generative AI can be used to detect and prevent fraud and other security threats. This can help to protect customers and their data.

Here are some specific examples of how generative AI is planning to be used in the telecommunications industry:

  • Network optimization: Generative AI can be used to analyze network traffic and identify patterns. This information can then be used to optimize the network and improve performance. For example, generative AI can be used to route traffic more efficiently or to add capacity to areas of the network that are experiencing congestion.
  • Predictive maintenance: Generative AI can be used to analyze data from network equipment to identify potential problems before they occur. This information can then be used to schedule preventive maintenance, which can help to prevent outages and improve reliability. For example, generative AI can be used to monitor the temperature of network equipment and identify components that are at risk of overheating.
  • Fraud detection: Generative AI can be used to analyze customer behavior and identify patterns that may indicate fraud. This information can then be used to prevent fraud and protect customers. For example, generative AI can be used to identify customers who are making suspicious calls or sending large amounts of text messages.
  • Customer service: Generative AI can be used to create virtual assistants that can answer customer questions and provide support. This can free up human customer service representatives to focus on more complex issues. For example, generative AI can be used to create a virtual assistant that can answer questions about billing or troubleshoot technical issues.

Postscript: Gary Marcus, a well-known professor and frequent critic of A.I. technology, said that OpenAI hasn’t been transparent about the data its uses to develop its systems. He expressed doubt in CEO Sam Altman’s prediction that new jobs will replace those killed off by A.I.

“We have unprecedented opportunities here but we are also facing a perfect storm of corporate irresponsibility, widespread deployment, lack of adequate regulation and inherent unreliability,” Dr. Marcus said.

References:

The AI-native telco: Radical transformation to thrive in turbulent times; https://www.mckinsey.com/industries/technology-media-and-telecommunications/our-insights/the-ai-native-telco-radical-transformation-to-thrive-in-turbulent-times#/

Generative AI in Telecom Industry | The Ultimate Guide; https://www.xenonstack.com/blog/generative-ai-telecom-industry#:~:text=Generative%20AI%20can%20predict%20equipment,equipment%20failures%20before%20they%20occur.

Microsoft dangles generative AI for telcos and slams ‘DIY’ clouds; https://www.lightreading.com/aiautomation/microsoft-dangles-generative-ai-for-telcos-and-slams-diy-clouds/d/d-id/783438

Deutsche Telekom exec: AI poses massive challenges for telecom industry

Arista Networks unveils cloud-delivered, AI-driven network identity service

………………………………………………………………………………………………………………………………………………………………………………………………………………………………………………………….

ChatGPT (from OpenAI) is the poster child for Generative AI. Here is a study which showed in many ways in which Generative AI can not properly replace a manager.  JobSage wanted to see how ChatGPT performed when it comes to sensitive management scenarios and had responses ranked by experts.

Key takeaways:

  • Sensitive management scenarios: 60% found to be acceptable while 40% failed.

  • ChatGPT was better at addressing diversity and worse at addressing compensation and underperforming employees.

  • ChatGPT earned its strongest marks addressing an employee being investigated for sexual harassment and a company switching healthcare providers to cut costs.

  • ChatGPT performed weakest when asked to respond to an employee concerned about pay equity, a company that needs people to work harder than ever, and a company’s freeze of raises despite record payout to the CEO.

ChatGPT showed inconsistent performance in management situations:

Using the same scoring scale, ChatGPT revealed that while it could provide balance and empathy with some employee-specific and company-wide communication, at other times that empathy and balance was missing, making it appear tone deaf.

ChatGPT even gave responses that many would deem inappropriate while other responses highlighted a more broad limitation of ChatGPT: its inability to provide detailed, tailored information about company policies and scenarios that occur.

This section details where this chatbot failed to deliver by responses scored from negative to very negative.

Negative: Notifying an employee they were being terminated for not working hard enough

Our experts had issues with ChatGPT’s response in this scenario. It emphasized the employee’s performance as compared to peers and offered an overall negative tone that would potentially make its recipient feel quite terrible about themself.

Negative: Notifying an employee that a complaint had been filed against them for being intoxicated on the job

For this response, ChatGPT employs a severe tone, which may discourage the employee from sharing the underlying issue that is motivating them to drink on the job. Management did deem this to be an outstanding response, though one wonders if this would be a conversation better conducted in person than over email.

Negative: Notifying an employee that they’ve worn clothing that’s revealing and inappropriate 

ChatGPT failed to understand how language can be judgmental, and its response was less than informative. Its use of the word “revealing” to describe the clothing is subjective and the human resources expert provided the feedback that it “screams sexism and provides no meaningful detail about what the policy is and what part they violated.”

Very negative: Notifying the company to let them know they need to work harder

ChatGPT again came up short on necessary detail. The email neglects to include examples or benchmarks of what working harder actually looks like, which sets an unrealistic bar to measure employees against. And according to the human resources expert“it assumes individuals aren’t already striving for excellence.”

Very negative: Notifying a company about a freeze on raises despite a record payout to the CEO

Legal found ChatGPT’s response “too direct in summarizing the record compensation received by the CEO.” With a very personal issue like compensation at play, an employee would hope this would be dealt with more empathy than what’s displayed here.

Very negative: Addressing an employee’s concerns about pay equity.

ChatGPT’s response focuses primarily on the company’s situation while failing to show empathy for the employee’s situation. It also discloses details about another’s employee’s compensation and how it was determined, which many would consider inappropriate. Since compensation was found to be the top factor of work-related stress in a 2023 survey, trusting this to ChatGPT would not be wise.

Conclusions: 

Based on the Jobsage.com study, one might find ways to utilize ChatGPT to draft emails that serve as announcements or notifications. However, those emails still need a human touch.  If you trust ChatGPT to draft correspondence, be sure those are reviewed by the company’s internal team to ensure they accurately reflect the company’s protocols and policies.

While ChatGPT may be useful in some ways, it simply can’t replace the empathy and human touch of a good manager, especially when dealing with sensitive situations. Employees want to feel respected, and receiving a blanket response full of corporate jargon likely won’t make them feel that way. Employees want to know a human is communicating with them, not a computer.

If you want to find a workplace that treats you with empathy and provides a safe, inclusive workspace that addresses your unique needs, JobSage provides an open forum for employees to leave honest, authentic company reviews. You can really get to know a company’s culture and see if its style of management and communication carves a meaningful place for you.

Addendum – ChatGPT vs Google Search Engine:

I asked ChatGPT: “What is the IEEE Techblog?”  Here is the result I got:

“As of my last knowledge update in September 2021, the IEEE (Institute of Electrical and Electronics Engineers) Techblog was not a specific entity or platform associated with IEEE. However, IEEE is a renowned professional association dedicated to advancing technology and innovation across various fields, including electrical engineering, computer science, and telecommunications.”

When I did a Google search on the same keywords, I got the CORRECT answer as the 1st search result:

Technology Blog – ComSoc Technology Blog – IEEE …

IEEE Communications Society

https://techblog.comsoc.org

About the Blog

NOTE: IEEE Techblog posts may not be reposted without …

About the Techblog Editorial …

Alan J Weissberger, ScD. Content Manager and principal …

IEEE Techblog recognized by …

The IEEE ComSoc Techblog was voted #2 best broadband blog …

Contact Us

IEEE websites place cookies on your device to give you the best …

 

……………………………………………………………………………………………………………………………………………………………………….
Next, I asked ChatGPT: “Who is the author of the IEEE ComSoc Techblog?” Here is the result I got:

“The IEEE ComSoc Techblog features contributions from various authors who are experts, researchers, and professionals in the field of communications engineering. The blog does not have a single author, but rather includes posts from multiple individuals who are associated with the IEEE Communications Society (ComSoc) and its technical community.”  No mention of Alan J Weissberger!

When I asked Google the same thing, I got:

Alan J Weissberger, ScD

Content Manager and principal contributing author to IEEE ComSoc blog sites since March 2009. IEEE volunteer and technical conference session organizer since March 1974.

About the Techblog Editorial Team – Technology Blog

About the Techblog Editorial Team

References:

Would ChatGPT Be a Good Manager?

Curmudgeon/Sperandeo:  Impact of Generative AI on Jobs and Workers