Blackboxstocks, Inc. is a financial technology and social media hybrid platform offering real-time proprietary analytics and news for stock and options traders of all levels. Our web-based software employs “predictive technology” enhanced by artificial intelligence to find volatility and unusual market activity that may result in the rapid change in the price of a stock or option. Blackbox continuously scans the NASDAQ, New York Stock Exchange, CBOE, and all other options markets, analyzing over 10,000 stocks and up to 1,500,000 options contracts multiple times per second. We provide our users with a fully interactive social media platform that is integrated into our dashboard, enabling our users to exchange information and ideas quickly and efficiently through a common network. We recently introduced a live audio/video feature that allows our members to broadcast on their own channels to share trade strategies and market insight within the Blackbox community. Blackbox is a SaaS company with a growing base of users that spans 42 countries; current subscription fees are $99.97 per month or $959.00 annually. For more information, go to: www.blackboxstocks.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.
CEO Form 4. On February 27th, the SEC released a Form 4 filing by CEO Gust Kepler that reported Mr. Kepler’s purchase of 1,130,002 BLBX shares on February 23rd at a price of $3 per share. The purchased increased Mr. Kepler’s direct common stock holding to 3,462,070 shares. According to the Company, this was a private transaction not conducted on an exchange. Mr. Kepler also owned 3,269,998 Series A Preferred shares as of December 27, 2022 that can be converted into common shares.
Investor Reaction. On Monday, BLBX shares rose 47% to close at $0.81 on 16.8 million shares traded. Normal average daily volume is 554,000 shares and the last time BLBX shares traded consistently in the $3 level was back in 2021, excluding a one-time spike in the share price in April 2022.
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.
Will Tesla Investors be Inspired or Disappointed on March 1 (Investor Day)?
Tesla’s Investor Day is March 1st. The lead-up to these events is usually filled with speculation of how the founder, Elon Musk, may surprise EV fans and the investment community. Tesla’s (TSLA) innovations and unique marketing and distribution have made it the most valuable car company in the world. Part of that marketing is the mystique and confidence Musk brings whenever he has an audience. The company is also inspiring as it is less than 20 years in the making and is leading a revolution in how automobiles are built, driven, and fueled.
As plans are kept under wraps, most of the rumors as to what to expect fall in the category of speculation. Below are some of the most likely ideas from past announcements from Tesla and across the internet since the meeting date was announced.
Battery Production
Sourcing raw materials for batteries to make certain new EVs have all the needed components is becoming a concern among car manufacturers.
News has leaked of a proposed $3.6 billion Giga factory to produce up to 100 Gwh of batteries. The factory is expected to be in Nevada and eventually be used to assemble the Tesla semi when production eventually starts.
Tesla is expected to build a processing facility to make lithium hydroxide from spodumene concentrate in Corpus Christie, Texas. The location is good for shipping, and it is close to sources of sulfuric acid from the oil industry. This would be the first lithium hydroxide production facility in the U.S. If true, it would help Tesla fulfill the raw material sourcing requirements of the Inflation Reduction Act to qualify its cars for the $7,500 federal tax credit.
Those deals are at market prices; Tesla would reap the profits from processing the spodumene concentrate into hydroxide, but the bulk of the profit from the material supply accrues to the mining company. Tesla has hinted previously of plans to enter the lithium mining business.
The $25,000 EV
First mentioned in 2020, Tesla’s proposed $25,000 car earned the nickname “fluffy pillow” after Musk showed a picture of an object covered by a blanket that many thought resembled a large pillow. The project was put on hold in early 2022 when Musk said Tesla had too much on its plate.
Tesla’s existing best sellers, the Model 3 and Model Y, have been around for a while, a new model, whether it is the truck or an affordable entry level car would freshen up the line-up.
New Factory
Tesla’s production goals put it at or near capacity. The current factory capacity is listed as 1.9 million vehicles per year. The current goal is six million cars a year by 2026. This would require the expansion of existing plants and then some. A new factory takes three years to design, construct, and get rolling. So planning would have to start now. Musk is more likely to build a new plant than change his production goals.
Thoughts from across the internet suggest this could be in Indonesia or Mexico. Cars built in Mexico could qualify for the $7500 tax credit to purchasers.
Capital Raise
To accomplish the above requires money. Currently, there is construction in progress building out Tesla’s German and Texas factories. Billions more would be needed to implement other plans.
There is as of recent reporting, $22 billion in cash on Tesla’s balance sheet. This is a snapshot of quarter-end and not an accurate representation of the company’s finances. Offsetting this large number is $15 billion in trade payables and $7 billion in accrued payables, much of which is due soon.
Tesla may have to go to the market to raise cash for projects that will be presented on March 1st.
About Tesla Day
The investor event will be live-streamed from Tesla’s Gigafactory in Texas, with some of the company’s institutional and retail investors attending in person. According to Tesla’s press release, investors will be able to see its most advanced production line as well as discuss long-term expansion plans, the generation 3 platform, and capital allocation.
What Sectors Outperformed the Market after the PCE Inflation Shock?
When an investor inquires, “What stocks do well with high inflation?” they are often asking, “What sectors do well with rising interest rates?,” because inflation expectations often drive rate moves. The text book response usually given are: consumer staples, banks and financials, and commodities. The PCE indexes are considered the Fed’s preferred indicator of inflation trends. The PCE surprised markets on the high side when released on February 24th. What can investors now expect from higher-than-forecast inflation?
Rather than look at old information on what outperforms the overall market when inflation expectations rise, I thought it would be informative and more useful to see what is outperforming under current 2023 conditions and climate. The chart below and the remainder of this simple study is a snapshot three hours after the news settled in among investors (11:30am ET, February 24th).
There were five S&P sectors that outperformed the S&P 500 a few hours after the inflation number showed an almost across-the-board acceleration in price increases. At this point, the S&P 500 had already fallen 1.31%.
Beating the S&P larger index, but the worst of the five outperformers was Health Care (XLV). The Health sector is considered to be a necessity that consumers find a means to pay for regardless of cost. Within the sector there are companies providing goods and services that are more embraced by investors than others. Within the XLV, many stocks were green after the report.
Outperforming the Health Care sector were stocks making up the Industrial Sector (XLI). This includes large industrial manufacturers like John Deere, General Electric, and Caterpillar. Many of these companies have contracts well out into the future that assures business. What is not ordinarily assured is the cost of manufacturing which can go up with inflation. A number of the top holdings in XLI barely budged on the morning – GE was up .08%, Honeywell was down .18%, and UPS was down just .20%.
Almost even with the Industrial Sector was Consumer Staples (XLP). As with Health Care and to a lesser degree Industrials this sector is where money moves to during inflationary periods. Consumers may be postpone a new car purchase, but they’ll keep their buying habits unchanged for products produced by Colgate, Coca-Cola, Proctor and Gamble, or cigarette manufacturers.
Performing second best after the inflation numbers was the Utility sector (XLU). Again this follows the mindset that consumers can only cutback on water, electricity, and natural gas so much. It is more likely that cutbacks would come in other areas like entertainment, or technology. Technology was the worst performing sector.
The top performer, although still modestly negative, was the Financial sector. This includes insurance, banks and credit card companies, as well as investment firms. Banks, particularly those with a higher percentage of traditional banking business, benefit from a steepening yield curve. Banks use cash as their product line. They borrow short from customers, and lend longer term. As the yield curve steepens, their net income can be expected to rise. This may explain why two of the top three holdings were positive after the report, JP Morgan (JPM), and Wells Fargo (WFC). Brokerage firms also may benefit as accounts uninvested balances can be a source of revenue as financial firms earn interest on them. Rising rates means every balance they can earn on creates additional income.
Larger Index Observations
As indicated earlier, technology was the worst-performing sector. This causes the tech heavy Nasdaq to far underperform the other major indexes. The best performing a few hour after the open was the Dow Industrials, which is comprised of just 30 industrial stocks, many paying consistent dividends. The second best performer, beating both the Dow and S&P 500 was the Russell 2000 Small-Cap index. Small-cap stocks tend to be less affected when borrowing costs change, and tend to have more of their end customers located domestically. The U.S.-based customers is an advantage to smaller stocks when rising rates cause rising dollar values. A rising dollar makes goods or services from the U.S. more expensive overseas.
Take Away
The textbook reply to questions related to rising rates, inflation, and sector rotation in stocks held up after the surprise PCE index increase. Banks, and necessities like heat and consumer goods outperformed. Also small-cap stocks did not disappoint, they also held up better than the overall large cap universe.
One difficulty small and even microcap investors face is that information is less available on many of these companies. And there are a lot of them, including in the sectors that outperform with inflation. One easy way to find which smaller companies are rising to the top is Channelchek’s Market Movers tab. This can be viewed throughout the trading day by clicking here for the link.
Firm improves financial flexibility, eliminates mandatory annual principal payments under new all-revolver facility with more favorable terms, extended maturity date
STAMFORD, Conn.–(BUSINESS WIRE)– Information Services Group (ISG) (Nasdaq: III), a leading global technology research and advisory firm, today announced it has successfully amended its $140 million credit facility at more favorable terms, to improve the firm’s financial flexibility.
The new credit agreement amends the previous agreement entered into on March 10, 2020. Key updates include:
Converting the previous term and revolving loan into an all-revolving credit facility
Eliminating $4.3 million of mandatory annual principal payments due in 2023 and 2024
Extending the maturity date of the previous agreement by three years, to February 2028
“Our amended credit facility greatly enhances our financial flexibility and offers further validation of our robust business performance that enabled these enhancements,” said Michael P. Connors, chairman and CEO of ISG. “We thank our lenders for their partnership and confidence in our ability to deliver long-term sustainable growth and value for our shareholders.”
BofA Securities Inc. was the Sole Lead Arranger and Sole Bookrunner on the transaction.
Additional details about the amended credit agreement can be found in the Form 8-K ISG filed today with the U.S. Securities and Exchange Commission, a link to which can be found on ISG’s website.
Forward-Looking Statements
This communication contains “forward-looking statements” which represent the current expectations and beliefs of management of ISG concerning future events and their potential effects. Statements contained herein including words such as “anticipate,” “believe,” “contemplate,” “plan,” “estimate,” “target,” “expect,” “intend,” “will,” “continue,” “should,” “may,” and other similar expressions, are “forward-looking statements” under the Private Securities Litigation Reform Act of 1995. These forward-looking statements are not guarantees of future results and are subject to certain risks and uncertainties that could cause actual results to differ materially from those anticipated. Those risks relate to inherent business, economic and competitive uncertainties and contingencies relating to the businesses of ISG and its subsidiaries including without limitation: (1) failure to secure new engagements or loss of important clients; (2) ability to hire and retain enough qualified employees to support operations; (3) ability to maintain or increase billing and utilization rates; (4) management of growth; (5) success of expansion internationally; (6) competition; (7) ability to move the product mix into higher margin businesses; (8) general political and social conditions such as war, political unrest and terrorism; (9) healthcare and benefit cost management; (10) ability to protect ISG and its subsidiaries’ intellectual property or data and the intellectual property or data of others; (11) currency fluctuations and exchange rate adjustments; (12) ability to successfully consummate or integrate strategic acquisitions; (13) outbreaks of diseases, including coronavirus, or similar public health threats or fear of such an event; and (14) engagements may be terminated, delayed or reduced in scope by clients. Certain of these and other applicable risks, cautionary statements and factors that could cause actual results to differ from ISG’s forward-looking statements are included in ISG’s filings with the U.S. Securities and Exchange Commission. ISG undertakes no obligation to update or revise any forward-looking statements to reflect subsequent events or circumstances.
About ISG
ISG (Information Services Group) (Nasdaq: III) is a leading global technology research and advisory firm. A trusted business partner to more than 800 clients, including 75 of the world’s top 100 enterprises, ISG is committed to helping corporations, public sector organizations, and service and technology providers achieve operational excellence and faster growth. The firm specializes in digital transformation services, including automation, cloud and data analytics; sourcing advisory; managed governance and risk services; network carrier services; strategy and operations design; change management; market intelligence and technology research and analysis. Founded in 2006, and based in Stamford, Conn., ISG employs more than 1,300 digital-ready professionals operating in more than 20 countries—a global team known for its innovative thinking, market influence, deep industry and technology expertise, and world-class research and analytical capabilities based on the industry’s most comprehensive marketplace data. For more information, visit www.isg-one.com.
No two hearts beat alike. The size and shape of the heart can vary from one person to the next. These differences can be particularly pronounced for people living with heart disease, as their hearts and major vessels work harder to overcome any compromised function.
MIT engineers are hoping to help doctors tailor treatments to patients’ specific heart form and function, with a custom robotic heart. The team has developed a procedure to 3D print a soft and flexible replica of a patient’s heart. They can then control the replica’s action to mimic that patient’s blood-pumping ability.
The procedure involves first converting medical images of a patient’s heart into a three-dimensional computer model, which the researchers can then 3D print using a polymer-based ink. The result is a soft, flexible shell in the exact shape of the patient’s own heart. The team can also use this approach to print a patient’s aorta — the major artery that carries blood out of the heart to the rest of the body.
To mimic the heart’s pumping action, the team has fabricated sleeves similar to blood pressure cuffs that wrap around a printed heart and aorta. The underside of each sleeve resembles precisely patterned bubble wrap. When the sleeve is connected to a pneumatic system, researchers can tune the outflowing air to rhythmically inflate the sleeve’s bubbles and contract the heart, mimicking its pumping action.
The researchers can also inflate a separate sleeve surrounding a printed aorta to constrict the vessel. This constriction, they say, can be tuned to mimic aortic stenosis — a condition in which the aortic valve narrows, causing the heart to work harder to force blood through the body.
Doctors commonly treat aortic stenosis by surgically implanting a synthetic valve designed to widen the aorta’s natural valve. In the future, the team says that doctors could potentially use their new procedure to first print a patient’s heart and aorta, then implant a variety of valves into the printed model to see which design results in the best function and fit for that particular patient. The heart replicas could also be used by research labs and the medical device industry as realistic platforms for testing therapies for various types of heart disease.
“All hearts are different,” says Luca Rosalia, a graduate student in the MIT-Harvard Program in Health Sciences and Technology. “There are massive variations, especially when patients are sick. The advantage of our system is that we can recreate not just the form of a patient’s heart, but also its function in both physiology and disease.”
Rosalia and his colleagues report their results in a study appearing today in Science Robotics. MIT co-authors include Caglar Ozturk, Debkalpa Goswami, Jean Bonnemain, Sophie Wang, and Ellen Roche, along with Benjamin Bonner of Massachusetts General Hospital, James Weaver of Harvard University, and Christopher Nguyen, Rishi Puri, and Samir Kapadia at the Cleveland Clinic in Ohio.
Print and Pump
In January 2020, team members, led by mechanical engineering professor Ellen Roche, developed a “biorobotic hybrid heart” — a general replica of a heart, made from synthetic muscle containing small, inflatable cylinders, which they could control to mimic the contractions of a real beating heart.
Shortly after those efforts, the Covid-19 pandemic forced Roche’s lab, along with most others on campus, to temporarily close. Undeterred, Rosalia continued tweaking the heart-pumping design at home.
“I recreated the whole system in my dorm room that March,” Rosalia recalls.
Months later, the lab reopened, and the team continued where it left off, working to improve the control of the heart-pumping sleeve, which they tested in animal and computational models. They then expanded their approach to develop sleeves and heart replicas that are specific to individual patients. For this, they turned to 3D printing.
“There is a lot of interest in the medical field in using 3D printing technology to accurately recreate patient anatomy for use in preprocedural planning and training,” notes Wang, who is a vascular surgery resident at Beth Israel Deaconess Medical Center in Boston.
An Inclusive Design
In the new study, the team took advantage of 3D printing to produce custom replicas of actual patients’ hearts. They used a polymer-based ink that, once printed and cured, can squeeze and stretch, similarly to a real beating heart.
As their source material, the researchers used medical scans of 15 patients diagnosed with aortic stenosis. The team converted each patient’s images into a three-dimensional computer model of the patient’s left ventricle (the main pumping chamber of the heart) and aorta. They fed this model into a 3D printer to generate a soft, anatomically accurate shell of both the ventricle and vessel.
The team also fabricated sleeves to wrap around the printed forms. They tailored each sleeve’s pockets such that, when wrapped around their respective forms and connected to a small air pumping system, the sleeves could be tuned separately to realistically contract and constrict the printed models.
The researchers showed that for each model heart, they could accurately recreate the same heart-pumping pressures and flows that were previously measured in each respective patient.
“Being able to match the patients’ flows and pressures was very encouraging,” Roche says. “We’re not only printing the heart’s anatomy, but also replicating its mechanics and physiology. That’s the part that we get excited about.”
Going a step further, the team aimed to replicate some of the interventions that a handful of the patients underwent, to see whether the printed heart and vessel responded in the same way. Some patients had received valve implants designed to widen the aorta. Roche and her colleagues implanted similar valves in the printed aortas modeled after each patient. When they activated the printed heart to pump, they observed that the implanted valve produced similarly improved flows as in actual patients following their surgical implants.
Finally, the team used an actuated printed heart to compare implants of different sizes, to see which would result in the best fit and flow — something they envision clinicians could potentially do for their patients in the future.
“Patients would get their imaging done, which they do anyway, and we would use that to make this system, ideally within the day,” says co-author Nguyen. “Once it’s up and running, clinicians could test different valve types and sizes and see which works best, then use that to implant.”
Ultimately, Roche says the patient-specific replicas could help develop and identify ideal treatments for individuals with unique and challenging cardiac geometries.
“Designing inclusively for a large range of anatomies, and testing interventions across this range, may increase the addressable target population for minimally invasive procedures,” Roche says.
This research was supported, in part, by the National Science Foundation, the National Institutes of Health, and the National Heart Lung Blood Institute.
Comtech Telecommunications Corp. engages in the design, development, production, and marketing of products, systems, and services for advanced communications solutions in the United States and internationally. It operates in three segments: Telecommunications Transmission, Mobile Data Communications, and RF Microwave Amplifiers. The Telecommunications Transmission segment provides satellite earth station equipment and systems, over-the-horizon microwave systems, and forward error correction technology, which are used in various commercial and government applications, including backhaul of wireless and cellular traffic, broadcasting (including HDTV), IP-based communications traffic, long distance telephony, and secure defense applications. The Mobile Data Communications segment provides mobile satellite transceivers, and computers and satellite earth station network gateways and associated installation, training, and maintenance services; supplies and operates satellite packet data networks, including arranging and providing satellite capacity; and offers microsatellites and related components. The RF Microwave Amplifiers segment designs, develops, manufactures, and markets satellite earth station traveling wave tube amplifiers (TWTA) and broadband amplifiers. Its amplifiers are used in broadcast and broadband satellite communication; defense applications, such as telecommunications systems and electronic warfare systems; and commercial applications comprising oncology treatment systems, as well as to amplify signals carrying voice, video, or data for air-to-satellite-to-ground communications. The company serves satellite systems integrators, wireless and other communication service providers, broadcasters, defense contractors, military, governments, and oil companies. Comtech markets its products through independent representatives and value-added resellers. The company was founded in 1967 and is headquartered in Melville, New York.
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.
Investor Meetings. We hosted Comtech CEO Ken Peterman and CFO Michael Bondi for a series of investor meetings in South Florida last week. In the meetings, CEO Peterman outlined the current progress made and future opportunities under his strategy to right the ship and grow from there.
The Present. Management spent time reviewing the actions already taken in regard to implementing the ONE Comtech vision. We expect the initial benefits of bringing the Company under one roof, including cost savings, more efficient use of capital, and the capture of additional business, will begin to flow into operating results in a noticeable way during the second half of fiscal 2023.
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.
Image: Marine Corps Warfighting Laboratory MAGTAF Integrated Experiment (MCWL) 160709-M-OB268-165.jpg
War in Ukraine Accelerates Global Drive Toward Killer Robots
The U.S. military is intensifying its commitment to the development and use of autonomous weapons, as confirmed by an update to a Department of Defense directive. The update, released Jan. 25, 2023, is the first in a decade to focus on artificial intelligence autonomous weapons. It follows a related implementation plan released by NATO on Oct. 13, 2022, that is aimed at preserving the alliance’s “technological edge” in what are sometimes called “killer robots.”
Both announcements reflect a crucial lesson militaries around the world have learned from recent combat operations in Ukraine and Nagorno-Karabakh: Weaponized artificial intelligence is the future of warfare.
“We know that commanders are seeing a military value in loitering munitions in Ukraine,” Richard Moyes, director of Article 36, a humanitarian organization focused on reducing harm from weapons, told me in an interview. These weapons, which are a cross between a bomb and a drone, can hover for extended periods while waiting for a target. For now, such semi-autonomous missiles are generally being operated with significant human control over key decisions, he said.
Pressure of War
But as casualties mount in Ukraine, so does the pressure to achieve decisive battlefield advantages with fully autonomous weapons – robots that can choose, hunt down and attack their targets all on their own, without needing any human supervision.
This month, a key Russian manufacturer announced plans to develop a new combat version of its Marker reconnaissance robot, an uncrewed ground vehicle, to augment existing forces in Ukraine. Fully autonomous drones are already being used to defend Ukrainian energy facilities from other drones. Wahid Nawabi, CEO of the U.S. defense contractor that manufactures the semi-autonomous Switchblade drone, said the technology is already within reach to convert these weapons to become fully autonomous.
Mykhailo Fedorov, Ukraine’s digital transformation minister, has argued that fully autonomous weapons are the war’s “logical and inevitable next step” and recently said that soldiers might see them on the battlefield in the next six months.
Proponents of fully autonomous weapons systems argue that the technology will keep soldiers out of harm’s way by keeping them off the battlefield. They will also allow for military decisions to be made at superhuman speed, allowing for radically improved defensive capabilities.
Currently, semi-autonomous weapons, like loitering munitions that track and detonate themselves on targets, require a “human in the loop.” They can recommend actions but require their operators to initiate them.
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, James Dawes, Professor, Macalester College.
By contrast, fully autonomous drones, like the so-called “drone hunters” now deployed in Ukraine, can track and disable incoming unmanned aerial vehicles day and night, with no need for operator intervention and faster than human-controlled weapons systems.
Calling for a Timeout
Critics like The Campaign to Stop Killer Robots have been advocating for more than a decade to ban research and development of autonomous weapons systems. They point to a future where autonomous weapons systems are designed specifically to target humans, not just vehicles, infrastructure and other weapons. They argue that wartime decisions over life and death must remain in human hands. Turning them over to an algorithm amounts to the ultimate form of digital dehumanization.
Together with Human Rights Watch, The Campaign to Stop Killer Robots argues that autonomous weapons systems lack the human judgment necessary to distinguish between civilians and legitimate military targets. They also lower the threshold to war by reducing the perceived risks, and they erode meaningful human control over what happens on the battlefield.
This composite image shows a ‘Switchblade’ loitering munition drone launching from a tube and extending its folded wings. U.S. Army AMRDEC Public Affairs
The organizations argue that the militaries investing most heavily in autonomous weapons systems, including the U.S., Russia, China, South Korea and the European Union, are launching the world into a costly and destabilizing new arms race. One consequence could be this dangerous new technology falling into the hands of terrorists and others outside of government control.
The updated Department of Defense directive tries to address some of the key concerns. It declares that the U.S. will use autonomous weapons systems with “appropriate levels of human judgment over the use of force.” Human Rights Watch issued a statement saying that the new directive fails to make clear what the phrase “appropriate level” means and doesn’t establish guidelines for who should determine it.
But as Gregory Allen, an expert from the national defense and international relations think tank Center for Strategic and International Studies, argues, this language establishes a lower threshold than the “meaningful human control” demanded by critics. The Defense Department’s wording, he points out, allows for the possibility that in certain cases, such as with surveillance aircraft, the level of human control considered appropriate “may be little to none.”
The updated directive also includes language promising ethical use of autonomous weapons systems, specifically by establishing a system of oversight for developing and employing the technology, and by insisting that the weapons will be used in accordance with existing international laws of war. But Article 36’s Moyes noted that international law currently does not provide an adequate framework for understanding, much less regulating, the concept of weapon autonomy.
The current legal framework does not make it clear, for instance, that commanders are responsible for understanding what will trigger the systems that they use, or that they must limit the area and time over which those systems will operate. “The danger is that there is not a bright line between where we are now and where we have accepted the unacceptable,” said Moyes.
Impossible Balance?
The Pentagon’s update demonstrates a simultaneous commitment to deploying autonomous weapons systems and to complying with international humanitarian law. How the U.S. will balance these commitments, and if such a balance is even possible, remains to be seen.
The International Committee of the Red Cross, the custodian of international humanitarian law, insists that the legal obligations of commanders and operators “cannot be transferred to a machine, algorithm or weapon system.” Right now, human beings are held responsible for protecting civilians and limiting combat damage by making sure the use of force is proportional to military objectives.
If and when artificially intelligent weapons are deployed on the battlefield, who should be held responsible when needless civilian deaths occur? There isn’t a clear answer to that very important question.
Image: Silver Peak Lithium Mine, Nevada – Ken Lund (Flickr)
The Lithium Dip May Be Worth Exploring
Lithium (Li) was once synonymous with treating depression. Today the mineral is more often discussed as part of the subject of sustainable energy storage, specifically batteries. So it’s ironic that the recent stock price movement of a number of companies tied to lithium may have depressed some investors, as February has seen a sudden depression in values. The primary reason for the decline in lithium stocks may actually be a net plus for miners and others tied to production. This thinking is outlined below.
Many companies involved in Li exploration and/or production were up on the year along with the overall market. Late last week and carrying over to today, many of these stocks have fallen dramatically. The reason for the sudden decline coincided with the largest EV battery manufacturer, Contemporary Amperex Technology’s (CATL) announcement that it will cut the price it charges for Li-ion batteries.
As seen in the chart below, Shares of the larger lithium miners Albemarle ALB (ALB), SQM (SQM), Livent (LTHM), Piedmont Lithium (PLL), and Lithium Americas (LAC) are down between 7% and 14% with much of that drop coming in the past few trading days. Smaller lithium mining operations like LithiumBank Resources Corp. (LBNKF), and Century Lithium Corp. (CYDVF) fared much better, outperforming the more established larger companies.
CATL seems to have aimed to maintain or grow its market share as a battery manufacturer. Any price war they may have started is likely to have a direct impact on competitors. Even car manufacturers that are involved in battery sales may shed some profitability, but is it necessarily a negative for companies involved in mining or refining?
CATL plans on pricing its batteries on a lithium-price-linked calculation. With this, 50% of each battery will benchmark to lithium carbonate, which would largely embed the price of lithium in its Li-ion product. The rest of the batteries will key off of the spot market for lithium carbonate.
Spot prices for lithium carbonate are up about ninefold over the past few years as the growth in EV demand and other battery-operated products has stressed the global lithium supply chain. So while CATL has decided to discount batteries, the production costs are unlikely to fall. The move may instead place greater demand on lithium carbonate. If production doesn’t keep up with, what should spark greater demand for Li-ion batteries, miners may benefit. If correct, this could suggest the declines in mining stock prices related to CATL’s new pricing policy, may be considered as an entry point for investors that had been looking for a price dip.
As for battery makers, this may have more permanently drained value. CATL is about 68% of the mainland Chinese EV battery manufacturing industry. Other battery producers may have to similarly adjust their pricing models to compete. This group includes Panasonic, LG Energy, Samsung, and SK Innovations that also tumbled this month.
Take Away
Mining analysts discuss supply and demand, or deficit and surplus, when adjusting forecasts. If demand grows as a result of the large battery manufacturer CATL discounting prices, and this discounting causes others to follow, the result could be a larger lithium deficit that could raise the price of the mineral per USD/metric-ton. Time will tell.
Will AI Learn to Become a Better Entrepreneur than You?
Contemporary businesses use artificial intelligence (AI) tools to assist with operations and compete in the marketplace. AI enables firms and entrepreneurs to make data-driven decisions and to quicken the data-gathering process. When creating strategy, buying, selling, and increasing marketplace discovery, firms need to ask: What is better, artificial or human intelligence?
A recent article from the Harvard Business Review, “Can AI Help You Sell?,” stated, “Better algorithms lead to better service and greater success.” The attributes of the successful entrepreneur, such as calculated risk taking, dealing with uncertainty, keen sense for market signals, and adjusting to marketplace changes might be a thing of the past. Can AI take the place of the human entrepreneur? Would sophisticated artificial intelligence be able to spot market prices better, adjust to expectations better, and steer production toward the needs of consumers better than a human?
In one of my classes this semester, students and I discussed the role of AI, deep machine learning, and natural language processing (NLP) in driving many of the decisions and operations a human would otherwise provide within the firm. Of course, half of the class felt that the integration of some level of AI into many firms’ operations and resource management is beneficial in creating a competitive advantage.
However, the other half felt using AI will inevitably disable humans’ function in the market economy, resulting in less and less individualism. In other words, the firm will be overrun by AI. We can see that even younger college students are on the fence about whether AI will eliminate humans’ function in the market economy. We concluded as a class that AI and machine learning have their promises and shortcomings.
After class, I started thinking about the digital world of entrepreneurship. E-commerce demands the use of AI to reach customers, sell goods, produce goods, and host exchange—in conjunction with a human entrepreneur, of course.
However, AI—machine learning or deep machine learning—could also be tasked with creating a business-based model, examining the data on customers’ needs, designing a web page, and creating ads. Could AI adjust to market action and react to market uncertainty like a human? The answer may be a resounding yes! So, could AI eliminate the human entrepreneur?
Algorithm-XLab explains deep machine learning as something that “allows computers to solve complex problems. These systems can even handle diverse masses of unstructured data set.” Algorithm-XLab compared deep learning with human learning favorably, stating, “While a human can easily lose concentration, and possibly make a mistake, a robot won’t.”
This statement by Algorithm-XLab challenges the idea that trial and error leads to greater market knowledge and better enables entrepreneurs to provide consumers with what they are willing to buy. The statement also portrays the marketplace as a process where people have perfect knowledge and an equilibrium point, and it implies that humans do not have specialized knowledge of time and place.
The use of AI and its tools of deep learning and language processing do have their benefits from a technical standpoint. AI can determine how to produce hula hoops better, but can it determine whether to produce them or devote energy elsewhere? If entrepreneurs discover market opportunities, they must weigh the advantages and disadvantages of their potential actions. Will AI have the same entrepreneurial foresight?
The acquisition of market knowledge can take humans years to acquire; AI is much faster at it than humans would be. For example, the Allen Institute for AI is “working on systems that can take science tests, which require a knowledge of unstated facts and common sense that humans develop over the course of their lives.” The ability to process unstated, scattered facts is precisely the kind of characteristic we attribute to entrepreneurs. Processes, changes, and choices characterize the operation of the market, and the entrepreneur is at the center of this market function.
There is no doubt that contemporary firms use deep learning for strategy, operations, logistics, sales, and record keeping for human resources (HR) decision-making, according to a Bain & Company article titled “HR’s New Digital Mandate.” While focused on HR, the digital mandate does lend itself to questioning the use of entrepreneurial thinking and strategy conducted within a firm. After AI has learned how to operate a firm using robotic process automation and NLP capacities to their maximum, might it outstrip the human natural entrepreneurial abilities?
AI is used in everyday life, such as self-checkout at the grocery store, online shopping, social media interaction, dating apps, and virtual doctor appointments. Product delivery, financing, and development services increasingly involve an AI-as-a-service component. AI as a service minimizes the costs of gathering and processing customer insights, something usually associated with a team of human minds projecting key performance indicators aligned with an organizational strategy.
The human entrepreneur has a competitive advantage insofar as handling ambiguous customer feedback and in effect creating an entrepreneurial response and delivering satisfaction. We seek to determine whether AI has replaced human energy in some areas of life. Can AI understand human uneasiness or dissatisfaction, or the subjectivity of value felt by the consumer? AI can produce hula hoops, but can it articulate plans and gather the resources needed to produce them in the first place?.
In what, if any, entrepreneurial functions can AI outperform the human entrepreneur? The human entrepreneur is willing to take risks, adjust to the needs of consumers, pick up price signals, and understand customer choices. Could the human entrepreneur soon become an extinct class? If so, would machine learning and natural processing AI understand the differences between free and highly regulated markets? If so, which would it prefer, or which would it create?
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.
