One Stop Systems, Inc. (OSS) designs and manufactures innovative AI Transportable edge computing modules and systems, including ruggedized servers, compute accelerators, expansion systems, flash storage arrays, and Ion Accelerator™ SAN, NAS, and data recording software for AI workflows. These products are used for AI data set capture, training, and large-scale inference in the defense, oil and gas, mining, autonomous vehicles, and rugged entertainment applications. OSS utilizes the power of PCI Express, the latest GPU accelerators and NVMe storage to build award-winning systems, including many industry firsts, for industrial OEMs and government customers. The company enables AI on the Fly® by bringing AI datacenter performance to ‘the edge,’ especially on mobile platforms, and by addressing the entire AI workflow, from high-speed data acquisition to deep learning, training, and inference. OSS products are available directly or through global distributors. For more information, go to www.onestopsystems.com.
Joe Gomes, Managing Director – Generalist Analyst, Noble Capital Markets, Inc.
Joshua Zoepfel, Research Associate, Noble Capital Markets, Inc.
Refer to the full report for the price target, fundamental analysis, and rating.
Getting More Work. Yesterday, One Stop Systems announced the Company has received a $1.3 million contract from the U.S. Army to develop vehicle visualization systems. OSS will be working closely with the Army to deliver prototypes later in 2023. The announcement comes on the heels of the $3 million order last month, and further signifies the Company’s capabilities in military applications.
Details. The contract from the U.S. Army is for the design, development, and prototypes for a ruggedized compute visualization system. Using OSS PCIe Gen 4 switched fabric technology and NVIDIA Jetson AGX Orin system-on-modules, the system will be used to support 360-degree visualization for U.S. Army ground vehicles.
Equity Research is available at no cost to Registered users of Channelchek. Not a Member? Click ‘Join’ to join the Channelchek Community. There is no cost to register, and we never collect credit card information.
This Company Sponsored Research is provided by Noble Capital Markets, Inc., a FINRA and S.E.C. registered broker-dealer (B/D).
*Analyst certification and important disclosures included in the full report. NOTE: investment decisions should not be based upon the content of this research summary. Proper due diligence is required before making any investment decision.
Getting to Know ChatGPT: A Shallow Dip into Its Current Functionality and Future Potential
ChatGPT and the underlying AI technology are, as near as anyone can tell, the next-level toolkit for research, communication, idea generation, and a million other uses. If you haven’t introduced yourself to it yet, leave plenty of time – getting started is easy, but getting yourself to stop may not be. Those of us that were around pre-internet may liken the first-time experience to the first time we gained access to the world wide web. The Sudden, much easier access to a world of information, puts one in a place where you don’t know what to try first.
Over the past couple of months, the now-familiar name, ChatGPT has made headlines. It quickly captivated the worlds imagination as an AI product that is likely to disrupt or destroy some industries while enhancing others. Obviously, this is of particular interest to investors. With this in mind, I sat down for an interview with ChatGPT; below are answers to questions that many investors are asking.
Channelchek (PH) – Am I able to interview Chatgpt?
ChatGPT – Hello! As an AI language model, I’m happy to answer any questions you may have. However, it’s important to keep in mind that I don’t have personal experiences or opinions like a human, and I can only provide information based on my training data. So feel free to ask me anything!
Channelchek (PH) – What do most users have ChatGPT to do for them?
ChatGPT – As an AI language model, ChatGPT can be used for a wide range of tasks, including:
Language translation: ChatGPT can be used to translate text from one language to another.
Content creation: ChatGPT can generate text for various types of content, such as articles, blog posts, and product descriptions.
Chatbot development: ChatGPT can be used to develop chatbots that can interact with users and provide information.
Sentiment analysis: ChatGPT can be used to analyze the sentiment of a piece of text, such as a social media post or a product review.
Question-answering: ChatGPT can be used to answer questions on a wide range of topics.
Text summarization: ChatGPT can be used to summarize long pieces of text into shorter, more manageable summaries.
Language modeling: ChatGPT can be used to train new models for specific domains, such as medical or legal language.
These are just a few examples of what ChatGPT can be used for. Its versatility and flexibility make it a powerful tool for many different applications.
Channelchek (PH) – From where do you pull your answers ChatGPT?
ChatGPT – As an AI language model, I don’t have pre-programmed answers. Instead, I generate responses to questions by analyzing patterns in large amounts of text data that I was trained on. Specifically, I was trained on a dataset of billions of words from various sources, including books, articles, websites, and other textual sources. During my training, I was exposed to a wide range of topics and writing styles, which helps me generate responses to many different types of questions.
When you ask me a question, I use natural language processing (NLP) techniques to analyze the question and generate a response based on patterns in the text data that I was trained on. I then use statistical models to determine the most likely response based on the context of the question and the patterns in the training data.
It’s important to note that my responses are only as accurate and reliable as the patterns that I learned during my training. While I strive to provide accurate and helpful information, I may not always get it right, and my responses may not reflect the views or opinions of OpenAI.
Channelchek (PH) – Are you at risk of having the response you generate slanted or biased based on users feedback adjusting your training ChatGPT?
ChatGPT – As an AI language model, I am designed to learn from the data that I am trained on, including the feedback that users provide to adjust my training. However, it’s important to be aware that the feedback that users provide can sometimes introduce biases into my training.
If the feedback is consistently biased in a particular direction, this could affect the accuracy and fairness of my responses. This is why it’s important to carefully monitor and evaluate any feedback that is used to adjust my training, and to ensure that it is representative of a wide range of perspectives.
To address this issue, OpenAI has implemented a number of safeguards to prevent bias and ensure that my training data is as accurate and diverse as possible. For example, the training data is carefully curated to include a wide range of sources and perspectives, and the training process is carefully monitored to ensure that biases are not introduced.
Additionally, OpenAI has implemented a number of techniques to help identify and mitigate any biases that may be present in the training data or feedback. For example, I am periodically evaluated to ensure that my responses are accurate and unbiased, and any issues that are identified are addressed through additional training or other adjustments to the model.
Channelchek (PH) – As an editor I write for Channelchek about stocks, the financial markets, the economy and business climate. Are you a good resource for current events related to these topics ChatGPT?
ChatGPT – As an AI language model, I can certainly provide you with information on current events related to stocks, financial markets, the economy, and the business climate. I have been trained on a vast amount of text data, including news articles and other sources related to these topics, so I can provide you with up-to-date information and insights on current events.
When asking me questions related to these topics, it’s important to provide me with as much context and specificity as possible so that I can provide you with the most accurate and relevant information. For example, if you are looking for information on a particular company or sector, you could provide me with the name of the company or sector, as well as any other relevant details or questions you may have.
However, it’s important to note that my responses are generated based on patterns in the text data that I was trained on, and may not reflect the views or opinions of OpenAI. Additionally, while I can provide you with information on current events and trends, I cannot provide investment advice or make predictions about future market performance. It’s always important to carefully evaluate information and seek the advice of a qualified financial professional before making investment decisions.
Channelchek (PH) – Do users ask you to forecast the stock market direction?
ChatGPT – Yes, users sometimes ask me to forecast the direction of the stock market. However, as an AI language model, I cannot make accurate predictions about future market performance. While I can provide information on current market trends and historical data, predicting the future direction of the stock market is a highly complex task that involves a range of economic, political, and social factors.
It’s important to note that investing in the stock market involves a certain degree of risk, and investors should always carefully evaluate market conditions and seek the advice of a qualified financial professional before making investment decisions. While I can provide general information and insights related to stocks and financial markets, I cannot provide investment advice or predict the future performance of individual stocks or the overall market.
Channelchek (PH) – Are you familiar with Channelchek?
ChatGPT – While I am not specifically programmed to be familiar with individual websites, I may have come across content from Channelchek during my training.
That being said, I can still provide you with general information on what Channelchek is. From my understanding, Channelchek is a financial information platform that provides independent research, analysis, and market commentary on publicly traded companies. It offers a range of tools and resources for investors and financial professionals, including market data, stock quotes, and research reports.
Channelchek’s focus is on providing unbiased and independent information to help investors make informed investment decisions.
Channelchek (PH) – Does your AI technology pose a risk to traditional internet search engines?
ChatGPT – My purpose is not to compete with traditional search engines like Google or Bing, but rather to complement them by providing an additional source of information and assistance to users. While I am capable of providing answers to a wide range of questions and generating responses to open-ended queries, I am not designed to replace traditional search engines or web browsing.
Search engines like Google and Bing are still the primary means by which users navigate the internet and find information, and they use a range of sophisticated algorithms and machine learning techniques to index and rank content on the web. While I am capable of processing natural language queries and generating responses, my training data is based on pre-existing content, which means that my responses are generated based on patterns in the text data that I was trained on, rather than direct access to the vast amounts of data on the internet.
Early Boolean Phrase Search Tool
Overall, AI language models like me are part of a larger ecosystem of tools and technologies that are designed to help users access and navigate the vast amount of information available online. While there may be some overlap between the capabilities of traditional search engines and AI language models, both serve different purposes and can work together to provide users with the most comprehensive and accurate information possible.
Channelchek (PH) – What industries are you likely to disrupt and which are you likely to augment or help build?
ChatGPT – As an AI language model, my capabilities are quite broad, and I have the potential to impact a wide range of industries and areas of society. Here are a few ways in which I could potentially disrupt or augment various industries:
Industries that could be disrupted:
Customer service: AI language models like me are already being used by many companies to automate and improve customer service interactions, and this trend is likely to continue. As AI technology improves, it could potentially replace many human customer service jobs.
Content creation: AI language models have the potential to automate certain types of content creation, such as news articles, product descriptions, and even social media posts. This could have a significant impact on the journalism and writing industries.
Education: AI language models could potentially disrupt the traditional education model by providing personalized learning experiences and automating certain types of teaching and grading.
Industries that could be augmented:
Healthcare: AI language models could help augment healthcare by providing more accurate and personalized diagnoses, and by automating certain types of administrative tasks.
Finance: AI language models could help augment finance by providing more accurate and data-driven investment advice, and by automating certain types of financial analysis.
Research: AI language models could help augment research by processing and analyzing vast amounts of data, and by identifying patterns and insights that might be difficult for humans to spot on their own.
Overall, the impact of AI language models like me on various industries will depend on a wide range of factors, including the development of the technology, the regulatory environment, and societal attitudes toward automation and AI. While there may be some industries that are more susceptible to disruption or augmentation than others, it’s important to approach these developments with a nuanced understanding of the potential benefits and risks.
Channelchek (PH) – Are users using ChatGPT to create social media bots to respond without human intervention likely to flood the internet?
ChatGPT – While it is technically possible for users to use AI language models like ChatGPT to create social media bots that can respond to messages without human intervention, I cannot speculate on whether this is likely to flood the internet.
The use of AI language models like ChatGPT could potentially make it easier and more accessible for users to create more sophisticated chatbots that can mimic human conversation more convincingly.
It’s also important to consider the potential impact of widespread use of social media bots on the quality and authenticity of online interactions. While chatbots can be useful in certain contexts, they can also be used to spread misinformation and propaganda or to manipulate public opinion. As with any technology, it’s important to approach the use of AI language models and chatbots in a responsible and ethical way, and to consider the potential risks and benefits of their use.
Channelchek (PH) – What do you call one that uses ChatGPT?
ChatGPT – There is no specific term for a person who uses ChatGPT or other AI language models, as these tools are designed to be accessible and usable by anyone with an internet connection.
However, a person who uses ChatGPT to create chatbots or other automated tools could be referred to as an AI developer or AI engineer. Similarly, a person who uses ChatGPT to conduct research or analysis in a specific field could be referred to as an AI researcher or analyst.
Channelchek (PH) – How much do you cost?
As an AI language model, I do not have a specific cost as I am not a commercial product. My purpose is to provide information and assistance to users like you, and I am freely accessible through various platforms that integrate my technology, including chatbots, voice assistants, and search engines.
Channelchek (PH) – Should I throw out the encyclopedias on my book shelf and rely instead on ChatGPT?
ChatGPT – Ultimately, whether or not to keep your encyclopedias depends on your personal preferences and how you prefer to access information. While AI language models like ChatGPT are convenient and accessible, they may not always provide the level of detail or accuracy that you require for a specific question or topic. So, it’s always a good idea to consult multiple sources of information to ensure that you have a well-rounded understanding of a given topic.
Channelchek (PH) – How does one get started using ChatGPT for research?
ChatGPT – Getting started with using ChatGPT for research can involve several steps. Here are a few basic steps you can follow:
Identify your research question or topic: Start by identifying the research question or topic you want to investigate. This will help you to focus your search and make the best use of ChatGPT.
Choose a ChatGPT platform: There are several platforms that integrate ChatGPT, including chatbots, voice assistants, and search engines. Choose a platform that best fits your needs and preferences.
Familiarize yourself with the platform: Once you have chosen a platform, take some time to explore and familiarize yourself with its features and capabilities. Many platforms offer tutorials and guides to help you get started.
Start asking questions: Once you are comfortable with the platform, start asking questions related to your research topic. Try to ask open-ended questions that will allow ChatGPT to provide more detailed and relevant answers.
Evaluate the results: As you receive answers from ChatGPT, evaluate the accuracy and relevance of the information. Keep in mind that ChatGPT is not perfect and may not always provide the most accurate or comprehensive information. Be sure to double-check any information you receive with other sources to ensure its accuracy.
Refine your search: If you are not finding the information you need, try refining your search by using more specific keywords or phrases.
Overall, using ChatGPT for research can be a valuable tool for gathering information and conducting preliminary investigations. However, it’s important to keep in mind that it is just one tool in the research process, and should be used in conjunction with other sources of information and research methods.
Wrap Up
It’s easy to comprehend how this technology, which will likely see stronger competition in the coming year, will quickly become something that is used every day to help streamline how we do our jobs, and find information in our personal lives. Unlike an internet search engine, queries produce individual results tailored to the individual question. The same question will recieve different phraseology if asked a minute later. Whereas Google or DuckDuckGo list websites that may provide the answer, ChatGPT responds using its own answer using artificial intelligence.
Getting started is as easy as going to OpenAI.com and navigating to Chat.OpenAI.com and providing an email and verification phone number. Click on my name below and write me, I’d love to hear what you are using it for.
One Stop Systems, Inc. (OSS) designs and manufactures innovative AI Transportable edge computing modules and systems, including ruggedized servers, compute accelerators, expansion systems, flash storage arrays, and Ion Accelerator™ SAN, NAS, and data recording software for AI workflows. These products are used for AI data set capture, training, and large-scale inference in the defense, oil and gas, mining, autonomous vehicles, and rugged entertainment applications. OSS utilizes the power of PCI Express, the latest GPU accelerators and NVMe storage to build award-winning systems, including many industry firsts, for industrial OEMs and government customers. The company enables AI on the Fly® by bringing AI datacenter performance to ‘the edge,’ especially on mobile platforms, and by addressing the entire AI workflow, from high-speed data acquisition to deep learning, training, and inference. OSS products are available directly or through global distributors. For more information, go to www.onestopsystems.com.
Joe Gomes, Managing Director – Generalist Analyst, Noble Capital Markets, Inc.
Joshua Zoepfel, Research Associate, Noble Capital Markets, Inc.
Refer to the full report for the price target, fundamental analysis, and rating.
Passing the Torch. In an unexpected move, yesterday the CEO of One Stop Systems, David Raun, announced he is stepping down from the position effective upon the appointment of his successor. We had spoken with Mr. Raun earlier this week about the 2023 vision and he came across as extremely enthusiastic with OSS’s opportunity set, especially related to the defense industry. The company has yet to identify a successor but has retained a search firm to help the Company find a suitable replacement. Notably, Mr. Raun will continue to serve as a member of the company’s Board of Directors.
Defense Experience Valued. Mr. Raun’s decision to step aside appears related to a desire to bring in a CEO with a background in the defense industry, as the near term opportunity set for OSS is in this space. As mentioned in the release, Mr. Raun stated, “I feel it’s time to bring in new leadership with deep experience and high-level contacts in the defense sector to scale the opportunities and growth.”
Equity Research is available at no cost to Registered users of Channelchek. Not a Member? Click ‘Join’ to join the Channelchek Community. There is no cost to register, and we never collect credit card information.
This Company Sponsored Research is provided by Noble Capital Markets, Inc., a FINRA and S.E.C. registered broker-dealer (B/D).
*Analyst certification and important disclosures included in the full report. NOTE: investment decisions should not be based upon the content of this research summary. Proper due diligence is required before making any investment decision.
Twitter’s New Data Fees Leave Scientists Scrambling for Funding – or Cutting Research
Twitter is ending free access to its application programming interface, or API. An API serves as a software “middleman” allowing two applications to talk to each other. An API is an accessible way to collect and share data within and across organizations. For example, researchers at universities unaffiliated with Twitter can collect tweets and other data from Twitter through their API.
Starting Feb. 9, 2023, those wanting access to Twitter’s API will have to pay. The company is looking for ways to increase revenue to reverse its financial slide, and Elon Musk claimed that the API has been abused by scammers. This cost is likely to hinder the research community that relies on the Twitter API as a data source.
The Twitter API launched in 2006, allowing those outside of Twitter access to tweets and corresponding metadata, information about each tweet such as who sent it and when and how many people liked and retweeted it. Tweets and metadata can be used to understand topics of conversation and how those conversations are “liked” and shared on the platform and by whom.
This article was republished with permission from The Conversation, a news site dedicated to sharing ideas from academic experts. It represents the research-based findings and thoughts of, Jon-Patrick Allem, Assistant Professor of Research in Population and Public Health Sciences, University of Southern California.
As a scientist and director of a research lab focused on collecting and analyzing posts from social media platforms, I have relied on the Twitter API to collect tweets pertinent to public health for over a decade. My team has collected more than 80 million observations over the past decade, publishing dozens of papers on topics from adolescents’ use of e-cigarettes to misinformation about COVID-19.
Twitter has announced that it will allow bots that it deems provide beneficial content to continue unpaid access to the API, and that the company will offer a “paid basic tier,” but it’s unclear whether those will be helpful to researchers.
Blocking Out and Narrowing Down
Twitter is a social media platform that hosts interesting conversations across a variety of topics. As a result of free access to the Twitter API, researchers have followed these conversations to try to better understand public attitudes and behaviors. I’ve treated Twitter as a massive focus group where observations – tweets – can be collected in near real time at relatively low cost.
The Twitter API has allowed me and other researchers to study topics of importance to society. Fees are likely to narrow the field of researchers who can conduct this work, and narrow the scope of some projects that can continue. The Coalition for Independent Technology Research issued a statement calling on Twitter to maintain free access to its API for researchers. Charging for access to the API “will disrupt critical projects from thousands of journalists, academics and civil society actors worldwide who study some of the most important issues impacting our societies today,” the coalition wrote.
@SMLabTO (Twitter)
The financial burden will not affect all academics equally. Some scientists are positioned to cover research costs as they arise in the course of a study, even unexpected or unanticipated costs. In particular, scientists at large research-heavy institutions with grant budgets in the millions of dollars are likely to be able to cover this kind of charge.
However, many researchers will be unable to cover the as yet unspecified costs of the paid service because they work on fixed or limited budgets. For example, doctoral students who rely on the Twitter API for data for their dissertations may not have additional funding to cover this charge. Charging for access to the Twitter API will ultimately reduce the number of participants working to understand the world around us.
The terms of Twitter’s paid service will require me and other researchers to narrow the scope of our work, as pricing limits will make it too expensive to continue to collect as much data as we would like. As the amount of data requested goes up, the cost goes up.
We will be forced to forgo data collection on some topic areas. For example, we collect a lot of tobacco-related conversations, and people talk about tobacco by referencing the behavior – smoking or vaping – and also by referencing a product, like JUUL or Puff Bar. I add as many terms as I can think of to cast a wide net. If I’m going to be charged per word, it will force me to rethink how wide a net I cast. This will ultimately reduce our understanding of issues important to society.
Difficult Adjustments
Costs aside, many academic institutions are likely to have a difficult time adapting to these changes. For example, most universities are slow-moving bureaucracies with a lot of red tape. To enter into a financial relationship or complete a small purchase may take weeks or months. In the face of the impending Twitter API change, this will likely delay data collection and potential knowledge.
Unfortunately, everyone relying on the Twitter API for data was given little more than a week’s notice of the impending change. This short period has researchers scrambling as we try to prepare our data infrastructures for the changes ahead and make decisions about which topics to continue studying and which topics to abandon.
If the research community fails to properly prepare, scientists are likely to face gaps in data collection that will reduce the quality of our research. And in the end that means a loss of knowledge for the world.
Recent Investment Trends Include Small-Cap Artificial Intelligence Stocks
C3 AI, sometimes written C3.ai, is an artificial intelligence platform that provides services for companies to build large-scale AI applications. Its stock had the fifth highest traded shares among Fidelity’s retail investors on Monday (February 6). This included a record-breaking $31.4 million worth of shares traded among the broker’s individual self-directed traders. According to Reuters, “Retail investors are piling up on small-cap firms that employ artificial intelligence amid intensifying competition between tech titans.” The article points to Google and Microsoft as examples of companies that expect AI to be the next meaningful driver of growth.
Investors, for their part, are looking to get ahead of any acquisition spree that deep-pocketed companies may embark on, which could include buying the advanced technology by acquiring small-cap tech firms.
Focus Heightened by ChatGPT
The spotlight ChatGPT finds itself in, three months after its launch, is indicicative of the interest in this technology amongst investors and users. With applications as numerous than one can think up, the technology could outdate many services provided by tech companies like Alphabet (GOOGL), or Microsoft (MSFT) – big tech has catching up to do. This seems to have created a race by cash rich companies to not be disrupted and left behind.
Investor’s recent focus on small companies in this space prefer those that are concentrated in AI technology. One main reason is that small-cap or microcap firms in this space are likely to have AI as a more concentrated part of their business. The bet being that whether the small company continues to grow independently, or is acquired by a larger firm looking to instantly be par with current technology, doesn’t much matter, it is a win for the investor if either occurs.
And it is a win, C3 AI stock rallied 46% last week, and climbed another 6.5% on Monday. It is now up 146% year to date.
Other Companies Involved
SoundHound AI, provides a voice AI platform services, and Thailand-based security firm Guardforce AI have more than doubled so far this year, while analytics firm BigBear.AI has increased ninefold.
US-listed shares of Baidu Inc climbed after the Chinese search engine indicated it would complete an internal test of a ChatGPT-style project called “Ernie Bot” next month.
Shares of Microsoft, which supports ChatGPT parent OpenAI, had been ratcheting up over the past month. The company is expected to make an announcement on their AI gained 1.5% in premarket trading ahead of the AI plans this week.
Google-owner Alphabet Inc said this week it would launch Bard, a chatbot service for developers, alongside its search engine.
Take Away
Change in technology that leads to improvements in daily lives has always been a focus of investors betting on which companies will outlast the others with “the next big thing.” These companies start out as small growth companies as Apple (AAPL) did in 1976. Then, a number of paths lay ahead. They either grow on their own like the Jobs/Wozniak computer maker did, get acquired for an early payday for investors and other stakeholders, or they can be outcompeted leaving investors with a non-performing asset.
Channelchek is a platform that specializes in bringing data and research on small-cap companies, including many varieties of new technology, to the investors that insist on being informed before they place a trade. Discover more on the industries of tomorrow by signing up for notifications in your inbox from Channelchek by registering here.
Discovering Why Trading is Halted on One of Your Stocks
Fair and orderly trading is an admirable goal of any system of exchange. As part of this ideal, exchanges, the SEC, and brokers can temporarily halt trading in stocks. The impact of news, or tripped circuit breakers designed to decelerate snowballing reactions (both human and programmed reactions), are the most common reasons to halt trading. There have also been events when a computer glitch, either feeding into an exchange or into the exchange’s systems, has triggered a pause or a halt. A total of 77 stocks were reportedly halted after the opening on the NYSE (January 24). They were all labeled “LULD,” this code is used to indicate it was a volatility trading pause. But officials at the NYSE say they’re still looking into it.
Reasons to Halt Trading
Companies listed on a U.S. stock exchange are responsible for notifying the listing exchange about any announcements or corporate developments that might affect trading in its stock. These often include:
Changes related to the financial health of the company
Changes in key management individuals
Major corporate transactions like restructurings or mergers
Significant positive or negative information about its products
Legal or regulatory developments that affect the company’s ability to conduct business
A circuit breaker has been reached due to volatility
Stock Halt Codes
Each day the exchanges list stocks as they are paused or halted and include a code to indicate the reason. The codes help market participants understand for how long it may be halted and for what general reason. It’s a good idea to be familiar with the codes shown below.
LUDP or LULD: Volatility trading pause (high volatility risk for investors).
T1: News pending (halted to give investors of all varieties ample time to evaluate).
H10: This is not enacted by the exchange but instead by the SEC (could be any number of regulatory reasons).
Image: Two of the many stocks halted on January 24, 2023 (NYSE Website)
The reason for the recent multiple stock pauses was available immediately on the NYSE website. Many of the stocks showed they were opening down substantially; the exchange says they are looking into this further.
There are also times when a circuit breaker stops trading across the market exchange. This is not the reason for the multiple pauses experienced in January, but also worth mentioning. There are three levels of halt based on size of the markets (S&P 500) move.
Level 1: 15-minute halt due to a 7% decrease from the S&P 500’s previous close
Level 2: 15-minute halt due to a 13% decrease from the S&P 500’s previous close
Level 3: Day-long halt due to a 20% decrease from the S&P 500’s previous close
Take Away
When the market opens and it is not business as usual, a lot of frustration can be saved by knowing market rules and finding resources to get a fast answer. While other traders wait for their favorite news service to report on it, going directly to the NYSE website to, in this case, get a listing of affected stocks and why, can put you ahead of those that are waiting for CNBC or another news outlet. Nasdaq also will post paused or halted stocks and use the same codes as above to indicate why.
Meme Stocks are Putting Up a Strong Offense – Is this a Positive Sign for the Broader Market?
During the first three weeks of 2023, meme stocks and crypto tokens, often viewed in the same category, have scored early. Have meme stock investors now come off the sidelines after the poor performance last year? In 2022 they completely failed to repeat their historic 2021 wins. So the current rally is a great sign.
Successful meme trading occurs when there is a mass movement by retail accounts. So far in 2023, like flipping a New Year’s switch, retail is again causing a commotion. And by looking at the trending hashtags and cashtags on Reddit and Twitter, fans are also making an increased volume of noise.
Looking at the 2023 performance chart above, the S&P 500 ($SPY) opened the year more positively than the prior year ended. While one obviously can not extrapolate out the current 1.59% return for the year, annualizing it helps bring the short period being measured into perspective. The overall market is running at a 30.50% pace this year. Wow.
The performance of GameStop ($GME), which was one of the original and among the most recognized meme stocks, is outperforming the overall market by double. While it is well off its high reached earlier this week, the above 3% return is running well ahead of the overall stock market.
The cryptocurrency in the group, the often maligned Dogecoin (DOGE.X), which is legendary as it started as a parody token, has been tracking Bitcoins (BTC.X) rise closely. DOGE is up over 18% on the year, averaging an increase near 1% per day.
AMC Entertainment ($AMC), which is off its high of almost 50% a few days ago, now has returned over 32% to those holding the stock. To put this in perspective, it has an annualized return in 2023, so far, of 628%. This likely has gotten ahead of itself, time will tell, but it is the clear MVP among the meme stocks to date.
Last year the overall market, despite being down near 20%,, trounced the meme stocks that have thus far put in a stellar showing in 2023.
Is Meme Rally a Reason for Optimism?
Retail dollars coming in off the sidelines and mounting enough of a drive to force values up so quickly indicates a mood change that may play out elsewhere in the financial markets. The average trade size of retail is so small that it indicates a large wave of willingness, if not outright optimism, that putting money in play will lead to gains. Similar forces are causing money to move into mutual funds and ETFs, which serves to put upward pressure on the overall market.
Wall Street’s so-called “fear gauge,” the Volatility Index ($VIX) dropped on average 1% a day since the start of the year. This is a spectacular trend. It now stands near its long-term average of 21; a reading above 30 is considered bearish. The $VIX was last near these levels in April of last year. The overall market stood 15% higher back then compared to today.
The Volatility Index has applications across digital assets as well. On a scale of 1-100, where 100 is overly greedy, The Crypto Fear and Greed Index stands near neutral at 52. This is also the most optimistic reading since April. It may be considered even more positive since the digital asset market is still digesting the “unprecedented” bankruptcy of crypto exchange FTX.
Meme mania has never been about macro; more about crowd behavior, commitment, and momentum. But there are fundamentals that are viewed by stock investors of all varieties that likely have fed into the burst of interest. First, economic data suggests that inflation is trending lower. This deceleration lessens the need for the Federal Reserve to put the brakes on the economy. The enthusiasm is just more pronounced among this style of retail traders that are loud and proud. They serve as cheerleaders to captivate the imagination of more traditional investors.
Take Away
The overall financial markets opened with a sigh of relief in 2023. Meme stocks and crypto opened the year with extreme optimism. The optimism isn’t without cause; a number of factors point to a much better environment than the dismal returns of last year.
Will this contagion, led by many small accounts, inspire further the larger individual and institutional investors to commit investments in the broader markets, there are many signs that suggest the year is starting that way, fear of missing out will build with each day that the markets move in a positive direction.
One Stop Systems, Inc. (OSS) designs and manufactures innovative AI Transportable edge computing modules and systems, including ruggedized servers, compute accelerators, expansion systems, flash storage arrays, and Ion Accelerator™ SAN, NAS, and data recording software for AI workflows. These products are used for AI data set capture, training, and large-scale inference in the defense, oil and gas, mining, autonomous vehicles, and rugged entertainment applications. OSS utilizes the power of PCI Express, the latest GPU accelerators and NVMe storage to build award-winning systems, including many industry firsts, for industrial OEMs and government customers. The company enables AI on the Fly® by bringing AI datacenter performance to ‘the edge,’ especially on mobile platforms, and by addressing the entire AI workflow, from high-speed data acquisition to deep learning, training, and inference. OSS products are available directly or through global distributors. For more information, go to www.onestopsystems.com.
Joe Gomes, Managing Director – Generalist Analyst, Noble Capital Markets, Inc.
Joshua Zoepfel, Research Associate, Noble Capital Markets, Inc.
Refer to the full report for the price target, fundamental analysis, and rating.
New Contract. One Stop Systems announced a new $3 million order from a prime military contractor. OSS commenced shipments in the fourth quarter of 2022, with the remaining units to be delivered in the first half of 2023. We view the announcement as further validation of OSS’s capabilities for military applications.
Details. Using its 4UV compute accelerator systems, OSS is upgrading a radar simulation system operated by the DoD Missile Defense Agency. The systems are being deployed in edge mobile radar systems and datacenters where they will be used for lab and field artificial intelligence training.
Equity Research is available at no cost to Registered users of Channelchek. Not a Member? Click ‘Join’ to join the Channelchek Community. There is no cost to register, and we never collect credit card information.
This Company Sponsored Research is provided by Noble Capital Markets, Inc., a FINRA and S.E.C. registered broker-dealer (B/D).
*Analyst certification and important disclosures included in the full report. NOTE: investment decisions should not be based upon the content of this research summary. Proper due diligence is required before making any investment decision.
In the future, the energy needed to run the powerful computers on board a global fleet of autonomous vehicles could generate as many greenhouse gas emissions as all the data centers in the world today.
That is one key finding of a new study from MIT researchers that explored the potential energy consumption and related carbon emissions if autonomous vehicles are widely adopted.
The data centers that house the physical computing infrastructure used for running applications are widely known for their large carbon footprint: They currently account for about 0.3 percent of global greenhouse gas emissions, or about as much carbon as the country of Argentina produces annually, according to the International Energy Agency. Realizing that less attention has been paid to the potential footprint of autonomous vehicles, MIT researchers built a statistical model to study the problem. They determined that 1 billion autonomous vehicles, each driving for one hour per day with a computer consuming 840 watts, would consume enough energy to generate about the same amount of emissions as data centers currently do.
The researchers also found that in over 90 percent of modeled scenarios, to keep autonomous vehicle emissions from zooming past current data center emissions, each vehicle must use less than 1.2 kilowatts of power for computing, which would require more efficient hardware. In one scenario — where 95 percent of the global fleet of vehicles is autonomous in 2050, computational workloads double every three years, and the world continues to decarbonize at the current rate — they found that hardware efficiency would need to double faster than every 1.1 years to keep emissions under those levels.
“If we just keep the business-as-usual trends in decarbonization and the current rate of hardware efficiency improvements, it doesn’t seem like it is going to be enough to constrain the emissions from computing onboard autonomous vehicles. This has the potential to become an enormous problem. But if we get ahead of it, we could design more efficient autonomous vehicles that have a smaller carbon footprint from the start,” says first author Soumya Sudhakar, a graduate student in aeronautics and astronautics.
Sudhakar wrote the paper with her co-advisors Vivienne Sze, associate professor in the Department of Electrical Engineering and Computer Science (EECS) and a member of the Research Laboratory of Electronics (RLE); and Sertac Karaman, associate professor of aeronautics and astronautics and director of the Laboratory for Information and Decision Systems (LIDS). The research appears today in the January-February issue of IEEE Micro.
Modeling Emissions
The researchers built a framework to explore the operational emissions from computers on board a global fleet of electric vehicles that are fully autonomous, meaning they don’t require a backup human driver.
The model is a function of the number of vehicles in the global fleet, the power of each computer on each vehicle, the hours driven by each vehicle, and the carbon intensity of the electricity powering each computer.
“On its own, that looks like a deceptively simple equation. But each of those variables contains a lot of uncertainty because we are considering an emerging application that is not here yet,” Sudhakar says.
For instance, some research suggests that the amount of time driven in autonomous vehicles might increase because people can multitask while driving, and the young and the elderly could drive more. But other research suggests that time spent driving might decrease because algorithms could find optimal routes that get people to their destinations faster.
In addition to considering these uncertainties, the researchers also needed to model advanced computing hardware and software that didn’t exist yet.
To accomplish that, they modeled the workload of a popular algorithm for autonomous vehicles, known as a multitask deep neural network, because it can perform many tasks at once. They explored how much energy this deep neural network would consume if it were processing many high-resolution inputs from many cameras with high frame rates simultaneously.
When they used the probabilistic model to explore different scenarios, Sudhakar was surprised by how quickly the algorithms’ workload added up.
For example, if an autonomous vehicle has 10 deep neural networks processing images from 10 cameras, and that vehicle drives for one hour a day, it will make 21.6 million inferences each day. One billion vehicles would make 21.6 quadrillion inferences. To put that into perspective, all of Facebook’s data centers worldwide make a few trillion inferences each day (1 quadrillion is 1,000 trillion).
“After seeing the results, this makes a lot of sense, but it is not something that is on a lot of people’s radar. These vehicles could actually be using a ton of computer power. They have a 360-degree view of the world, so while we have two eyes, they may have 20 eyes, looking all over the place and trying to understand all the things that are happening at the same time,” Karaman says.
Autonomous vehicles would be used for moving goods, as well as people, so there could be a massive amount of computing power distributed along global supply chains, he says. And their model only considers computing — it doesn’t take into account the energy consumed by vehicle sensors or the emissions generated during manufacturing.
Keeping Emissions in Check
To keep emissions from spiraling out of control, the researchers found that each autonomous vehicle needs to consume less than 1.2 kilowatts of energy for computing. For that to be possible, computing hardware must become more efficient at a significantly faster pace, doubling in efficiency about every 1.1 years.
One way to boost that efficiency could be to use more specialized hardware, which is designed to run specific driving algorithms. Because researchers know the navigation and perception tasks required for autonomous driving, it could be easier to design specialized hardware for those tasks, Sudhakar says. But vehicles tend to have 10- or 20-year lifespans, so one challenge in developing specialized hardware would be to “future-proof” it so it can run new algorithms.
In the future, researchers could also make the algorithms more efficient, so they would need less computing power. However, this is also challenging because trading off some accuracy for more efficiency could hamper vehicle safety.
Now that they have demonstrated this framework, the researchers want to continue exploring hardware efficiency and algorithm improvements. In addition, they say their model can be enhanced by characterizing embodied carbon from autonomous vehicles — the carbon emissions generated when a car is manufactured — and emissions from a vehicle’s sensors.
While there are still many scenarios to explore, the researchers hope that this work sheds light on a potential problem people may not have considered.
“We are hoping that people will think of emissions and carbon efficiency as important metrics to consider in their designs. The energy consumption of an autonomous vehicle is really critical, not just for extending the battery life, but also for sustainability,” says Sze.
Cathie Wood Reveals 2022’s Most Disruptive and Innovative Technologies
ARK Invest’s Cathie Wood penned a lookback-themed article about the innovations and disruptive companies of 2022. The purpose seemed to be to remind followers that although during the year, investors may have become disheartened with innovation, ‘look at the amazing opportunities that occurred.’ The innovations and companies highlighted were somewhat overlooked; following the path we are accustomed to from many breakthroughs, they fly under the radar. Then, suddenly they’re widely adopted. Below are many of her picks for innovation and companies she may now wish her funds held large positions in.
The Future of Internet
Suddenly everyone is talking about ChatGPT. According to Wood, artificial intelligence (AI), specifically, ChatGPT is advancing at a pace that is surprising even by standards set by earlier versions. This version of GPT-3, optimized for conversation, signed up one million users in just five days. By comparison, this onboarding of users is incredibly fast benchmarked against the original GPT-3, which took 24 months to reach the same level.
In 2022, TV advertising in the US underwent significant changes. Traditional, non-addressable, non-interactive TV ad spending dropped by 2% to $70 billion, according to Wood. Connected TV (CTV) ad spending on the same terms increased by 14% to ~$21 billion. Pure-play CTV operator Roku’s advertising platform revenue increased 15% year-over-year in the third quarter, the latest report available, while traditional TV scatter markets plummeted 38% year-over-year in the US. Roku maintained its position in the CTV market as the leading smart TV vendor in the US, accounting for 32% of the market.
Digital Wallets are replacing both credit cards and cash. In the category of offline commerce. They overtook cash as the top transaction method in 2020 and accounted for 50% of global online commerce volume in 2021. As an example of the growth, Square’s payment volume soared 193%, six times faster than the 30% increase in total retail spending 2019-2022 (relative to pre-COVID levels).
While overall e-commerce spending increased by 99% over the last three years, social commerce merchandise volume grew even faster. Shopify’s gross merchandise volume grew by 312%, almost four times faster than overall e-commerce and taking a significant share from other retail.
Underlying public blockchains continue to process transactions despite what may be going on surrounding the connected industries. Wood says it highlights that “their transparent, decentralized, and auditable ledgers could be a solution to the fraud and mismanagement associated with centralized, opaque institutions.” She explains, “After the FTX collapse, the share of trading volume on decentralized exchanges, which allow for trading without a central intermediary, rose 37% from 8.35% to 11.44%.
Genomic Revolution
Base editing and multiplexing have the potential to provide more effective CAR-T treatments for patients with otherwise incurable cancers. Cathie Wood provided an example from 2022 about a young girl in the UK with leukemia that went from hopeless in May to Canver-free in November.
In 2022 Dutch scientists at the Hubrecht Institute, UMC Utrecht, and the Oncode Institute used another form of gene editing called prime editing to correct the mutation that causes cystic fibrosis in human stem cells. Another example of how it is being adopted comes from Korean researchers at Yonsei University that used prime editing successfully to treat liver and eye diseases in adult mice.
CRISPR gene editing in Cathie’s words, “has delivered functional cures for beta-thalassemia and sickle cell disease.” She gives examples: CRISPR Therapeutics and Vertex Pharmaceuticals which together have treated more than 75 patients, resulting in some well-publicized “functional cures”. They are expecting FDA approval for Exa-Cel, the treatment for sickle cell and beta thalassemia, in early 2023.
In the category the Ark Invest founder referred to as other cell and gene therapies, she says in 2022, regulators approved several landmark cell and gene therapies. The examples she used to highlight this are Hemgenix for the treatment of Haemophilia B, Zyntelgo for beta thalassemia, Skysona for cerebral adrenoleukodystrophy, Yescarta and Breyanzi for Non-Hodgkin lymphoma, Tecartus for mantle cell lymphoma, and Carvykti and Abecma for multiple myeloma.
Liquid biopsies, blood tests via molecular diagnostic testing are enabling the early detection of colorectal cancer which, if discovered at or before stage 1, have a five-year survival rate greater than 90%. Late-stage or metastatic cancers account for more than 55% of deaths over a five-year period, but only 17% of new diagnoses.
Autonomous Technology & Robotics
During 2022 electric vehicle maker Tesla sales increased by 49% even as automobile sales declined by 8%. Tesla’s share of total auto sales in the US has increased to 3.8% from 1.4% in three years.
During 2022, GM expanded its autonomous driving taxi service to most of San Francisco in the first large-scale rollout in a major US city. Then it launched in both Phoenix and Austin late in the year. The automaker with a stodgy reputation, managed to compress the time to commercialization from nine years in San Francisco to just 90 days in Austin. Tesla, for its part, expanded access to its FSD (full self-driving) beta software to all owners in North America who had requested access.
By January 4, 2023, both Amazon and Walmart had begun deliveries using drones in select US cities. Autonomous logistics technology is no longer futuristic and is likely to continue being adopted and expanded.
Across the top 50 medical device companies, 90% rely on 3D printing for prototyping, testing, and even in some cases printing medical devices.
In 2022, SpaceX nearly doubled the number of rockets it launched to 61. It reused the same rocket in as few as 21 days, a dramatic improvement over the 356 days required for its first rocket reuse. Private Space Exploration is a reality. 61 rockets is an average of more than one per week.
Take Away
Hedge fund manager Cathie Wood took the new year as an opportunity to communicate examples of game-changing innovation that the equity market largely ignored in 2022. She finds these as confidence building that the premise of many of her managed funds is with merit. More importantly, in the face of market headwinds and media criticism, she wants these examples to help boost investor confidence “that ARK’s strategies are on the right side of change.” She tells readers, “innovation solves problems and has historically gained share during turbulent times.”
Image: Lung-on-a-Chip, National Center for Advancing Translational Sciences (Flickr)
Organ-On-A-Chip Models Allow Researchers to Conduct Studies Closer to Real-Life Conditions – and Possibly Grease the Drug Development Pipeline
Bringing a new drug to market costs billions of dollars and can take over a decade. These high monetary and time investments are both strong contributors to today’s skyrocketing health care costs and significant obstacles to delivering new therapies to patients. One big reason behind these barriers is the lab models researchers use to develop drugs in the first place.
Preclinical trials, or studies that test a drug’s efficacy and toxicity before it enters clinical trials in people, are mainly conducted on cell cultures and animals. Both are limited by their poor ability to mimic the conditions of the human body. Cell cultures in a petri dish are unable to replicate every aspect of tissue function, such as how cells interact in the body or the dynamics of living organs. And animals are not humans – even small genetic differences between species can be amplified to major physiological differences.
Fewer than 8% of successful animal studies for cancer therapies make it to human clinical trials. Because animal models often fail to predict drug effects in human clinical trials, these late-stage failures can significantly drive up both costs and patient health risks.
To address this translation problem, researchers have been developing a promising model that can more closely mimic the human body – organ-on-a-chip.
This article was republished with permission from The Conversation, a news site dedicated to sharing ideas from academic experts. It represents the research-based findings and thoughts of Chengpeng Chen, Assistant Professor of Chemistry and Biochemistry, University of Maryland, Baltimore County
As an analytical chemist, I have been working to develop organ and tissue models that avoid the simplicity of common cell cultures and the discrepancies of animal models. I believe that, with further development, organs-on-chips can help researchers study diseases and test drugs in conditions that are closer to real life.
What are Organs-On-Chips?
In the late 1990s, researchers figured out a way to layer elastic polymers to control and examine fluids at a microscopic level. This launched the field of microfluidics, which for the biomedical sciences involves the use of devices that can mimic the dynamic flow of fluids in the body, such as blood.
Advances in microfluidics have provided researchers a platform to culture cells that function more closely to how they would in the human body, specifically with organs-on-chips. The “chip” refers to the microfluidic device that encases the cells. They’re commonly made using the same technology as computer chips.
Not only do organs-on-chips mimic blood flow in the body, these platforms have microchambers that allow researchers to integrate multiple types of cells to mimic the diverse range of cell types normally present in an organ. The fluid flow connects these multiple cell types, allowing researchers to study how they interact with each other.
This technology can overcome the limitations of both static cell cultures and animal studies in several ways. First, the presence of fluid flowing in the model allows it to mimic both what a cell experiences in the body, such as how it receives nutrients and removes wastes, and how a drug will move in the blood and interact with multiple types of cells. The ability to control fluid flow also enables researchers to fine-tune the optimal dosing for a particular drug.
The lung-on-a-chip model, for instance, is able to integrate both the mechanical and physical qualities of a living human lung. It’s able to mimic the dilation and contraction, or inhalation and exhalation, of the lung and simulate the interface between the lung and air. The ability to replicate these qualities allows researchers to better study lung impairment across different factors.
Bringing Organs-On-Chips to Scale
While organ-on-a-chip pushes the boundaries of early-stage pharmaceutical research, the technology has not been widely integrated into drug development pipelines. I believe that a core obstacle for wide adoption of such chips is its high complexity and low practicality.
Current organ-on-a-chip models are difficult for the average scientist to use. Also, because most models are single-use and allow only one input, which limits what researchers can study at a given time, they are both expensive and time- and labor-intensive to implement. The high investments required to use these models might dampen enthusiasm to adopt them. After all, researchers often use the least complex models available for preclinical studies to reduce time and cost.
This chip mimics the blood-brain barrier. The blue dye marks where brain cells would go, and the red dye marks the route of blood flow. Vanderbilt University/Flickr
Lowering the technical bar to make and use organs-on-chips is critical to allowing the entire research community to take full advantage of their benefits. But this does not necessarily require simplifying the models. My lab, for example, has designed various “plug-and-play” tissue chips that are standardized and modular, allowing researchers to readily assemble premade parts to run their experiments.
The advent of 3D printing has also significantly facilitated the development of organ-on-a-chip, allowing researchers to directly manufacture entire tissue and organ models on chips. 3D printing is ideal for fast prototyping and design-sharing between users and also makes it easy for mass production of standardized materials.
I believe that organs-on-chips hold the potential to enable breakthroughs in drug discovery and allow researchers to better understand how organs function in health and disease. Increasing this technology’s accessibility could help take the model out of development in the lab and let it make its mark on the biomedical industry.
What’s a ‘Gig’ Job? How it’s Legally Defined Affects Workers’ Rights and Protections
The “gig” economy has captured the attention of technology futurists, journalists, academics and policymakers.
“Future of work” discussions tend toward two extremes: breathless excitement at the brave new world that provides greater flexibility, mobility and entrepreneurial energy, or dire accounts of its immiserating impacts on the workers who labor beneath the gig economy’s yoke.
This article was republished with permission from The Conversation, a news site dedicated to sharing ideas from academic experts. It represents the research-based findings and thoughts of David Weil, Visiting Senior Faculty Fellow, Ash Center for Democracy Harvard Kennedy School / Professor, Heller School for Social Policy and Management, Brandeis University.
These widely diverging views may be partly due to the many definitions of what constitutes “gig work” and the resulting difficulties in measuring its prevalence. As an academic who has studied workplace laws for decades and ran the federal agency that enforces workplace protections during the Obama administration, I know the way we define, measure and treat gig workers under the law has significant consequences for workers. That’s particularly true for those lacking leverage in the labor market.
While there are benefits for workers for this emerging model of employment, there are pitfalls as well. Confusion over the meaning and size of the gig workforce – at times the intentional work of companies with a vested economic interest – can obscure the problems gig status can have on workers’ earnings, workplace conditions and opportunities.
Defining Gig Work
Many trace the phrase “gig economy” to a 2009 essay in which editor and author Tina Brown proclaimed: “No one I know has a job anymore. They’ve got Gigs.”
Although Brown focused on professional and semiprofessional workers chasing short-term work, the term soon applied to a variety of jobs in low-paid occupations and industries. Several years later, the rapid ascent of Uber, Lyft and DoorDash led the term gig to be associated with platform and digital business models. More recently, the pandemic linked gig work to a broader set of jobs associated with high turnover, limited career prospects, volatile wages and exposure to COVID-19 uncertainties.
The imprecision of gig, therefore, connotes different things: Some uses focus on the temporary or “contingent” nature of the work, such as jobs that may be terminated at any time, usually at the discretion of the employer. Other definitions focus on the unpredictability of work in terms of earnings, scheduling, hours provided in a workweek or location. Still other depictions focus on the business structure through which work is engaged – a staffing agency, digital platform, contractor or other intermediary. Further complicating the definition of gig is whether the focus is on a worker’s primary source of income or on side work meant to supplement income.
Measuring Gig Work
These differing definitions of gig work have led to widely varying estimates of its prevalence.
A conservative estimate from the Bureau of Labor Statistics household-based survey of “alternative work arrangements” suggests that gig workers “in non-standard categories” account for about 10% of employment. Alternatively, other researchers estimate the prevalence as three times as common, or 32.5%, using a Federal Reserve survey that broadly defines gig work to include any work that is temporary and variable in nature as either a primary or secondary source of earnings. And when freelancing platform Upworks and consulting firm McKinsey & Co. use a broader concept of “independent work,” they report rates as high as 36% of employed respondents.
No consensus definition or measurement approach has emerged, despite many attempts, including a 2020 panel report by the National Academies of Sciences, Engineering, and Medicine. Various estimates do suggest several common themes, however: Gig work is sizable, present in both traditional and digital workplaces, and draws upon workers across the age, education, demographic and skill spectrum.
Why it Matters
As the above indicates, gig workers can range from high-paid professionals working on a project-to-project basis to low-wage workers whose earnings are highly variable, who work in nonprofessional or semiprofessional occupations and who accept – by choice or necessity – volatile hours and a short-term time commitment from the organization paying for that work.
Regardless of their professional status, many workers operating in gig arrangements are classified as independent contractors rather than employees. As independent contractors, workers lose rights to a minimum wage, overtime and a safe and healthy work environment as well as protections against discrimination and harassment. Independent contractors also lose access to unemployment insurance, workers’ compensation and paid sick leave now required in many states.
Federal and state laws differ in the factors they draw on to make that call. A key concept underlying that determination is how “economically dependent” the worker is on the employer or contracting party. Greater economic independence – for example, the ability to determine price of service, how and where tasks are done and opportunities for expanding or contracting that work based on the individual’s own skills, abilities and enterprise – suggest a role as an independent contractor.
In contrast, if the hiring party basically calls the shots – for example, controlling what the individual does, how they do their work and when they do it, what they are permitted to do and not do, and what performance is deemed acceptable – this suggests employee status. That’s because workplace laws are generally geared toward employees and seek to protect workers who have unequal bargaining leverage in the labor market, a concept based on long-standing Supreme Court precedent.
Making Work More Precarious
Over the past few decades, a growing number of low-wage workers find themselves in gig work situations – everything from platform drivers and delivery personnel to construction laborers, distribution workers, short-haul truck drivers and home health aides. Taken together, the grouping could easily exceed 20 million workers.
Many companies have incentives to classify these workers as independent contractors in order to reduce costs and risks, not because of a truly transformed nature of work where those so classified are real entrepreneurs or self-standing businesses.
Since gig work tends to be volatile and contingent, losing employment protections amplifies the precariousness of work. A business using misclassified workers can gain cost advantages over competitors who treat their workers as employees as required by the law. This competitive dynamic can spread misclassification to new companies, industries and occupations – a problem we addressed directly, for example, in construction cases when I led the Wage and Hour Division and more recently in several health care cases.
The future of work is not governed by immutable technological forces but involves volitional private and public choices. Navigating to that future requires weighing the benefits gig work can provide some workers with greater economic independence against the continuing need to protect and bestow rights for the many workers who will continue to play on a very uneven playing field in the labor market.
For Now, Innovation and Entrepreneurship Still Hold a High Place in the USA
Commentators worry that the United States might lose its dominance in innovation to Asian countries like China and Singapore. Many policymakers are intimidated by the R&D budgets of Asian countries and by their superior performance on international academic assessments. However, these concerns are misguided because the United States still dominates innovation.
The United States ranks second on the Global Innovation Index and scores the highest in the world on fifteen of eighty-one innovation indicators. The US innovation ecosystem continues to lead in the commercialization of research, and its universities are on the cutting edge of academic research. Other countries are expanding research budgets, but the United States’ genius is its ability to commercialize relevant innovations.
Innovations are only useful when they disrupt industries by transforming society and altering consumer preferences. Because innovations respond to market changes, anything can become an innovation, and the process is highly spontaneous. Unfortunately, too many countries are laboring under the assumption that government plans inevitably lead to innovation. Finding the next game changer is tremendously difficult due to the dynamism of consumer preferences.
US entrepreneurs appreciate that innovation is a freewheeling process rather than an object of grand design. That is why Silicon Valley, with its reverence for risk and failure, has been known for innovation. In her 2014 book, The Upside of Down: Why Failing Well is the Key to Success, Megan McArdle argues that the United States’ tolerance toward failure is a crucial pillar of prosperity because it promotes self-actualization, risk, and the continuous quest for innovation.
The United States’ rivals have eloquent five-year plans and extravagant budgets, but US innovation is undergirded by private institutions with a strong appetite for risk and iconoclastic thinking. Private venture-capital associations and research institutions searching for future pioneers are the primary players in US innovation. Government innovation plans are inherently conservative because they hinge on the success of targeted industries.
But, in the private sector, entrepreneurs are deliberately scouting for disruptors to undercut traditional industries by launching breakthrough products. The conformity of government bureaucracies is an enemy of the unorthodox thinking that spurs innovation. China is known for having a competent and meritocratic civil service, yet scholars contend that it lacks an innovative environment.
A key problem is that China focuses on competing with western rivals instead of developing new industries; innovation is perceived as a competition between China and its rivals rather than an activity pursued for its own sake. Consequently, US companies remain market leaders and are more adept at converting market information into innovative products than their Chinese counterparts. Unlike China, US entrepreneurship is not a function of geopolitics.
Meanwhile, some commentators suggest that the US education system is better at deploying talent due to its encouragement of unorthodox thinking. In contrast, Singapore and China have been criticized for emphasizing rote learning at the expense of critical thinking. For example, Singapore’s public sector is a model of excellence; however, despite government support, Singapore is yet to become an innovation hotbed.
Bryan Cheung, in an assessment of industrial policy in Singapore, comments on the failure of Singapore to translate research into innovation: “Even though Singapore ranks highly on global innovation indices, closer scrutiny reveals that it scores poorly on the sub-component of innovation efficiency.” A recent edition of the Global Innovation Index, using a global comparison, declared that “Singapore produces less innovation outputs relative to its level of innovation investments.”
Cheung explains that Singapore is heavily reliant on foreign talent to boost innovation: “Even the six ‘unicorns’ that Singapore has produced (Grab, SEA, Trax, Lazada, Patsnap, Razer) were all founded or co-founded by foreign entrepreneurs. In the Start-Up Genome (2021), Singapore also performed relatively poorly in ‘quality and access’ to tech talent, research impact of publications, and local market reach, which is unsurprising since innovation activity is concentrated in foreign hands.”
Asian countries are growing more competitive, but it will take decades before they develop the United States’ appetite for risk, market-driven innovations, and the uncanny ability to monetize anything. The United States’ spectacular economic performance and business acumen are based on its unique culture. Those who bet against the United States by downplaying its culture are bound to lose. The United States’ rivals are still catching up.
About the Author
Lipton Matthews is a researcher, business analyst, and contributor to Merion West, The Federalist, American Thinker, Intellectual Takeout, mises.org, and Imaginative Conservative. Visit his YouTube channel, here. He may be contacted at [email protected] or on Twitter (@matthewslipton)
