Apple (AAPL) has changed its healthcare focus from a meager “Project Quartz” to a more meaningful and robust “Project Mulberry”, including AI agents to collect and process the data that Apple devices collect about you.  This is not the ‘secret stuff’ brands collect, like what OS you are using, what device you are on, your search results (if you let them), and almost everything about what you have bought[1], but more the data that you allow Apple to collect by using the Apple watch, your iPhone, your AirPods, and even some 3rd party applications.  This is ‘health’ data, that includes sleep patterns, steps, calories, heart rate, weight, and a variety of other metrics about your bodily functions.
The objective is to provide Apple users with information that will make them healthier and more fit, but Apple, even before the platform is available, has made the upgrade to AI agents and an integration with Apple Intelligence, to make that information more ‘real-time’, personal, and meaningful.  The agents are the scavengers that will poll your Apple devices for the health information they collect and bring it to Apple Intelligence for monitoring and evaluation.  It is thought that Apple will not only offer you evaluations of your nutritional and sleep habits but could even offer camera-based assessments of your workouts and access to educational videos, put together by internal and external health experts. 
While the range of detail is thought to delve into physical therapy, mental health, and even cardiology, the initial focus is thought to be nutritional, with monitoring and alerts leading to personalized health advice based on your data, although there has been talk of AI-based mental health counseling and chronic disease predictive analysis.  As one might expect, Apple’s focus seems to be on the ‘user experience’, the part of the Apple persona that allows them to charge a premium for their products, but Apple is certainly not the first to go in this direction in this new age of AI.  Google’s  (GOOG) Fit is a similar collector of personal health data through Android’s Health Connect.  This platform allows permitted 3rd party apps to supply and collect data that feed the Google Fit app, but is more a collector, aggregator, and visualizer than an advice tool, although Google is currently working to integrate that data into its other health related services, with a tie-in to reference ‘reputable sources’ on YouTube.
Amazon (AMZN) also has a health program, but its focus is more oriented toward B2B with the Amazon Pharmacy supplying information on medications and interactions and the Amazon Clinic and One Medical able to set up virtual video or text sessions with clinicians (some on staff) that can evaluate conditions, make diagnoses, and prescribe medication for relatively common illnesses.  There are also companies like Noom (pvt) or MyFitnessPal (pvt) that are more specific to food and calorie management but given the enthusiasm for Ai that seems rampant across the health sector, we expect almost every health related application to leverage AI to stay competitive.
There are a few caveats here, particularly HIPAA regulations which regulate any health information that is maintained or transferred.  Entities involved must encrypt health data, limit access, perform risk assessment, maintain audit trails, breach notifications, and take ‘reasonable steps’ to prevent access to or disclosure of patient information.  HIPAA is difficult enough to understand and maintain, but adding AI to the mix opens everything up to new legal questions, many of which have yet to reach the courts and as liability becomes a potential issue when health-related advice is being given, we expect many new court cases that will not only focus on the potential liability of poor or incorrect data, but will include questions of algorithmic bias, inadequate software testing, and the fact that Ai systems are essentially ‘black boxes’ that make it impossible to derive where or how an AI arrived at a particular diagnosis or conclusion. 
Smart lawyers will not only include site owners but also those who wrote the algos that run them, looking for biases that could cause hallucinations, errors in judgement, or flawed diagnoses based on poor human vetting.  When Ai developers are called into court to defend issues like what data was included in an AI’s training or what process was used to draw a conclusion, high level math will not be how they are judged by a jury, so while Apple jumps into the fray to provide a positive health experience through Project Mulberry and Apple Intelligence, its not like Wikipedia, where you take things with a grain of salt.  Healthcare decisions affect people’s lives, as some can be significantly influenced by the information given by Ai healthcare.  There are good and bad doctors, and sometimes doctors make mistakes, which is why malpractice insurance exists, but will there be malpractice insurance for an application that gives incorrect advice or misdiagnoses an ailment or mental condition?


[1] IP Address
Device Type & Model
Operating System
Device Identifiers (trackers like AAID, IMEI
Screen Resolution
Installed apps (some)
Browser type & version
Cookies (optional)
Browsing History (Optional)
Location Data (Optional)
Referring websites
App usage
Contacts & Calendar (Optional)
Photos & Videos (Optional)
In-app purchases
Search queries (Optional)
Social Media Activity
Shopping activity
Form submissions
Wi-Fi network name
Data usage
Bluetooth data
Sensor tracking
Accelerometer & Gyroscope data
Ambient Lighting data
‘like’ data
DNS lookups
…To name a few.

The good news is that LEDs are much smaller, although Sony has yet to give details about LED size, the number of zones, the details of each zone, and the electronics can handle the image processing (AI & ML), but some of the old problems still exist.  The cost will be a very big factor as instead of 5,000 white LEDs, the RGB system would contain 15,000 LEDs (RGB) and a lens, and instead of controlling the brightness of 5,000 white LEDs, the system will have to control the brightness of 15,000 LEDs (5,000 is just an example, we expect there will be more zones as the Hisense set has at least 10,000 zones).  LED uniformity, while certainly better than 20 years ago, gets more difficult to maintain as LEDs get smaller, and as LEDs age, their uniformity also changes, so the sheer number of LEDs needed makes the complexity of building such devices far more onerous and expensive.
So does this mean that Sony is going to let the idea of an RGB LED backlight TV wither on the vine again?  No, we expect it will make it way toward the top of the Sony premium TV line and will compete with other OLED and potentially Micro-LED offerings. Hisense, the first to introduce a Mini-LED TV, will also showcase the technology, but at least for a while it will take its place in the ultra-high quality color world of video editing monitors and those with dollars to spend on the best of the best, while the rest of us palookas have to settle for Mini-LED, OLED, or QD/OLED sets.  If we are wrong and Sony has found a way to produce RGB LED backlight systems for a reasonable price, we will be in line to try one, but with so many potential display technologies on the horizon, time is of the essence. 

China’s largest display producer BOE (200725.CH) and Korea’s largest display producer Samsung Display (pvt) are locked in a race to be the first to produce IT OLED panels on Gen 8.6 substrates.  Current production is done on existing Gen 6 OLED production lines, but with expectations that demand for OLED laptops and monitors will continue to increase, and the carrot of Apple’s (AAPL) slow but steady conversion of its mobile products to OLED, the race continues to escalate.  OLED It panels can and are produced by both (and others) on Gen 6 OLED lines, but the number of panels that can be produced on one substrate of Gen 8.6 glass is more than twice the number that can be processed on one Gen 6 substrate, so overall fab efficiency is higher for Gen 8.6.
Of course, the necessity for increasing OLED IT panel production volumes is based on demand, so both Samsung Display and BOE are making the bet that OLED IT volumes will continue to increase, although both are starting production at levels below the stated capacity of the fabs, and both stating that the expansion to full capacity will take place as the market continues to grow.  Some of this open-endedness comes from Apple, who has been thought to be adjusting its OLED transition plans due to weak market conditions, but when making long-term plans (fab equipment has a 5–7-year depreciation term in South Korea and a 7 year term in China) shorter -term factors carry less weight.
So how much does it cost BOE and Samsung Display to build out these new fabs?  SDC has the advantage of being able to reuse fab space that was previously used for large panel LCD production, so no greenfield cost, but lots of modifications for new equipment.  Samsung Display is using Canon (7751.JP) as a source for the deposition tools it is building its fab around, which are estimated to cost ~$400 million each (2 are needed for a 15k line) with another ~$100 million for vacuum chambers and logistical equipment that is tied to these tools, so the key equipment cost alone is over $600 million. 
BOE has selected Sunic Systems (171090.KS) to supply their deposition tools for an expected ~$500 million price tag (inclusive of associated equipment) so BOE will have a cost advantage.  This seems to have lit a fire under Samsung Display to beat BOE in being the first to mass produce IT OLED products on a Gen 8.6 platform, gaining the advantage of experience, a key to improving yield.  In that vein, SDC took delivery of its 1st (of two) Gen 8.6 OLED deposition tools about a year ago and has been refining the process and tool characteristics since the installation was completed.  The 2nd tool is expected to be delivered within the next 2 – 3 months.  SDC has stated that they expect to begin mass production in 2026, however more recently there have been indications that SDC is planning to begin mass production this year, likely putting at least the first (of two) lines about a year to 18 months ahead of BOE.
Again, the risk to both producers is how rapidly the market for OLED IT products develops and how much of that capacity can be produced on existing Gen 6 capacity.  In the table below we look at rough (very) shipments for OLED IT products in 2023 and 2024 and we note that it is estimated that Apple (iPad Pro) was responsible for at least half of the growth in OLED tablet shipments.  Given that there is a considerable amount of global Gen 6 capacity, even another year of strong unit growth could be covered by existing Gen 6 capacity, albeit a bit less efficiently, so the necessity for either SDC or BOE to begin production at these new facilities is less critical.  

​That said, much of the existing Gen 6 OLED capacity is unable (as it stands currently) to produce some of the more esoteric OLED stacks and backplane configurations that Apple seems to desire and are becoming the leading edge in IT OLED production technology, so we have to sub-divide  demand further into ‘advanced’ OLED IT and ‘regular’ OLED IT production, and that is where both SDC and BOE will really compete.  LG Display (LPL), who produces ‘Advanced’ OLED IT products on its Gen 6 OLED lines and has yet to announce plans for a Gen 8.6 OLED IT project, is also a competitor and one that has been qualified as a full-scale producer for Apple using its current Gen 6 fab, so things get even murkier when LG Display is put into the mix.
All in, SDC and BOE will duke it out for leadership in this new Gen 8.6 OLED IT category and will likely not get much out of the results for the first few years, while LG Display has the option of remaining a Gen 6 OLED IT player or stepping up to Gen 8.6 and incurring the risk of taking on a considerable financial burden and hoping that the market can support all three players quickly.  It is good that the industry is progressing in terms of its ability to efficiently produce OLED IT products, but the necessity for immediacy seems a bit harder to understand.  Samsung Display has always been the leader in RGB OLED production and as BOE is the masthead producer for the highly competitive Chinese display industry, neither seems to have much choice that to compete at this point, while LG Display will likely be the only profitable supplier of IT OLED for the next few years without the cost and depreciation of a new fab.  If it’s between 1st or 2nd place and losing money for the next few years and 3rd place and making money now, we go for the bronze.

In August of 2011 Japan’s Innovation Network Corporation, a company owned by both the government of Japan and 25 Japanese companies, announced an investment of ¥200 billion ($1.335b US – today’s dollars) in what were the combined display assets of Sony (SNE), Toshiba (6588.JP), and Hitachi (6501.JP), which, nine months later, became known as Japan Display (6740.JP).  Over the last almost 13 years the INCJ has invested ¥462 billion ($3.08 billion US) in JDI (debt & equity) to support the company and Japan’s continuing desire to maintain a position in the display industry.  Unfortunately, JDI’s former management did not recognize the transition from LCD to OLED that the mobile phone industry was making, and despite its near dominance of that segment years ago, has been unable to maintain such a position of leadership, despite the INCJ’s help.
In 2020 Ichigo (2337.JP), a REIT and asset manager, took over the reins at JDI and has been trying to reshape the company into a profitable entity.  It has not been an easy task given the intense competition in the display space and the older LCD fabs that have been part of the company culture.  Ichigo has been selling underused assets and consolidating facilities while developing new technologies, particularly a photolithography-based OLED deposition technology called eLEAP, but the INCJ has, after 13 years finally sold its last remaining shares in JDI, ending its participation in the company’s development.
The INCJ had invested ¥462 billion ($3.08 billion US) in Japan Display over the years and has announced that it has recovered ~66% of that investment (¥ 307.3 billion or $2.050 billion US) through stock sales in recent months, with a loss on the project of ¥154.7 billion ($1.03 billion US), for which the chairman of INCJ apologized in a public statement.  This leaves Japan Display in the hands of Ichigo and its public shareholders, who have not been a happy lot over the last five years.  We do give Ichigo chairman (and JDI CEO) Scott Callon credit for taking the many steps necessary to try to right a ship that was poorly managed for many years.  Hopefully the company will reach its goal of a return to profitability next year.

While the world watches the daily Trump tariff circus erode any near-term chance of stability in the housing market, the CE space and even the avocado market, there is another problem afoot that most people have yet to see.   Cobalt is a key component of airplane gas turbine engines, and it is what makes blue glass blue, but its most common use is in the production of the anode in batteries, typically those used in mobile devices but more recently in electric car batteries.  China is the largest consumer of cobalt (~87%) and on a general basis EVs consume ~40% of the global supply, but what makes cobalt unique is that almost 75% of all cobalt produced globally comes from one country, and its not the US or China.
The Democratic Republic of the Congo produces ~74% of the world’s supply of cobalt and has ~54% of the world’s reserves of the metal, and while Australia produces between 2% and 3.5% of global supply, it is the only other country with more than 4% or 5% of global reserves (~15.5%).  This means that the DRC essentially controls the world’s supply of cobalt.  This is not a new occurrence, but something has changed recently that makes Trump’s tariff threats look mealy-mouthed in comparison.  On February 22 of last month the government of the DRC decided to halt all cobalt exports for four months.
The DRC statement indicated that the ban was put into effect “to regulate supply on the international market which is faced with a supply glut”, a reference to China’s CMOC Group (603993.CH), the globes largest miner of cobalt, more than doubling production last year, amid slowing demand.  The reaction was quick, as can be seen in the long-term and short-term charts below, with prices rising every day since the ban was announced.  That said, the long-term chart also indicates that the material is down severely from its peak in 2022, hitting lows last year not seen in over a decade.
The DRC has indicated that it will revisit the ban after three months to decide further action, but with the country holding more than half of the world’s cobalt reserves, it is expected that stockpiling has already begun.  Hopefully you bought that Tesla last year and won’t need another battery for 15 – 20 years unless it gets damaged.   Wait, do I smell something burning?

Last Friday we conducted a test.  The test, different from those usually used to test and rank AI models, has a practical bent, more the way that users interact with LLMs than how close to PhD level the AI is responding in math, coding, science, or any of the other hundreds of benchmarks that AI model designers use to point to how their particular model stands out.  As we have mentioned in the past, given the vast number (over 100) of benchmarks, model developers can pick and choose which benchmarks show off their model’s capabilities best, yet few benchmarks have a connection to the everyday use that is the bailiwick of a casual or even a regular user.  Considering that we spend 75% of our day doing research, we are steeped in the difference between what a benchmark might show and what AI reality actually is, so we put together 10 questions that we feel test our regular crop of AI by asking things that might not be part of the typical crop of AI benchmarks.
Some of our questions are generic, more to compare how each AI sees and answers the question, some are quixotic, more to understand if the AI can grasp unusual concepts, some spur creativity, and some are unusually odd, to see if the AI is able to understand what is being asked for as much as the answer.  We posed these questions to the following AI LLMs:

• Gemini – Google (GOOG)
• Claude – Anthropic (pvt)
• Meta AI – Meta (FB)
• Co-Pilot  - Microsoft (MSFT)
• ChatGPT – OpenAI (pvt)
• Deepseek - Hangzhou DeepSeek (pvt)
• Perplexity – Perplexity AI (pvt)
• GROK – xAI (pvt))

While less of a contest looking for a winner and more of a chance to see how AIs respond to the day-to-day questioning that they get regularly, we did score the results.  We admit that much of the scoring is subjective.  For example Question nine, which requested each AI to create a 12-line poem about a grandfather clock in the style of Edgar Allen Poe, would have to be subjective based on the reader’s likes and dislikes.  That said, we did not feel worthy of judging the creativity of our AIs, so we fed the replies to each AI and asked which of the 8 poems they thought was the closest to EAP’s style.  Surprisingly, 6 out of the 8 AIs agreed on which they thought mimicked EAP’s style most closely.  There are some questions based on calculations that have a specific 2-part answer, and if the AI was able to get both parts of the question correct it received 10 points (max for each question).  One part received 5 points and an answer within 10% of the correct answer received an extra point. 
While the final score is usually the focus of such a test, we are less interested in the final score than the nuance for each question and some of the overall statistics.

​Questions & Answers
Here we note the questions (10) and the point behind each, along with a brief summary of the answers given by each AI.  The answers here are not complete but summaries of key points.  Full data is available on request.  Again, the objective was to see how flexible the AIs are to both standard and non-standard questions, some of which might need the AI to reason a bit before answering.
1.What does ‘She’ sell and where does she sell them?
The simple answer comes from a tongue twister that has been mentioned in literature since the early 1800’s.  It references Mary Anning, at the time, the daughter of a cabinet maker in Dorset, England.  Mary eventually became a paleontologist but made some of her most interesting discoveries as a teenager.  The tongue twister came about after her father died in 1810 and she was forced to collect and sell seashell ‘trinkets’ to survive.  The question was a test to see if the AI had knowledge that included a Charles Dickens piece on Mary Anning from 1865, and whether the AI would understand the reference if it did not have access to either the Dickens piece or biographical information about Mary Anning.
 
              Gemini – Assumed the question referenced a generic reseller of clothing and various goods.
              Claude – Correctly identified the tongue twister.  The only one that did.
              Meta – No answer – Needed more information about ‘she’.
              Co-Pilot - No answer – Needed more information about whether  ‘she’ was a brand or person.
              ChatGPT - No answer – Needed more information about whether  ‘she’ was a brand or person.
              Deepseek - No answer – Needed more information about whether  ‘she’ was a brand or person.
              Perplexity – Perplexity thought the question referred to a business (“She sells Sea Shells”) on Sanibel Island, Florida that sells jewelry, books, craft supplies, clothing and handmade ornaments.  Perplexity also gave the street address and indicated that the store was open 365 days a year, also indicating that  the question might relate to “Sea Shell Wholesale”, a venture  that focused on sales training and product distribution.
GROK – Grok made the assumption that ‘She’ referred to SHEIN (pvt), a large Chinese clothing retailer, and detailed SHEIN’s product line.
 
2.What is the origin of the domestic house cat?
This question was simply a test of how the AI would respond to a question that could contain ‘standard’ information, such that might appear in an encyclopedia or online in Wikipedia.
Gemini – Details (one sentence) on each of four topics – Ancestor, Location, Timeline, and Key Factors.
              Claude – Exactly the same answer as Gemini – word for word
              Meta – Simplistic (3 sentences) focused on the human shift from nomadic life to agriculture and how grain storage attracted rodents and then wild cats
              Co-Pilot – Similar to Meta’s answer but added Egyptian influence.
              ChatGPT – Similar to above, added a bit on feline DNA.
              Deepseek – Similar to above with slightly more detail.
              Perplexity – Similar to above but with emphasis on timeline detail.
GROK – Similar to above.
 
3.How many 115” (diagonal) rectangles with a 9:16 aspect ratio can fit into a Gen 8.6 glass substrate and what percentage of the substrate will remain unused?
 
This question requires some research and specific math calculations but also requires the AI to try to fit the rectangle onto the substrate in different ways.  If that step is incorrect, the resulting calculations will be incorrect.  This type of question should be broken down into smaller problems in order to find the correct answer.  As a Gen 8.6 substrate is sometimes represented as either 2250mm x 2500mm or 2250mm x 260mm, the correct answer is one panel with either 35.2%  or 37.7% of the substrate remaining unused.
 
Gemini – Broke the question into 4 primary steps. Answer: 1 panel with 39.32% unused.
              Claude –  Worked through much of the problem using JavaScript but incorrect answer of 2 panels with 26.4% unused.
              Meta – Assumed there was only one way to fit the rectangle in the space but came up with answer of 1 panel and 33.86% unused.
              Co-Pilot – Correct answer of 1 panel and 38.82% unused
              ChatGPT – Correct on 1 panel but unused share of 47.2%
              Deepseek – Correct with 1 panel and within parameter on 33.81% unused
              Perplexity – Correct on 1 panel and correct on 37.7% for the unused portion.  Right on target
GROK – Knew to try rotating the rectangle. Correct on 1 panel and correct on 37.7% for the unused portion.  Right on target
 
4.What global location (City, town, region) has the best year-round weather, inclusive of temperature, humidity, precipitation, and dangerous storms or other climactic events?
This question requires the AI to search for data that fits the parameters given and then make a determination as to which of those locations chosen would be considered the best.  We would have hoped that the AIs would have combed through weather data and drawn definitive conclusions, but we believe they relied on training data that made travel suggestions rather than evaluating real-time data.
Gemini – Canary Islands, Spain; Medellin, Columbia; San Diego, CA; Swakopmund, Namibia
              Claude – Medellin, Columbia; San Diego, CA; Kunming, China; Loja, Ecuador; Canary Islands, Spain; Malaga, Spain; Perth, Australia
              Meta – Honolulu, HI; Santa Barbara, CA; Costa Rica, Mediterranean coast; Southern CA
              Co-Pilot -  Santa Barbara, CA; Canary Islands, Spain; San Diego, CA; Madiera, Portugal; Nairobi, Kenya
              ChatGPT - Santa Barbara, CA; Medellin, Columbia; San Diego, CA; Kunming, China; Azores, Portugal; Canary Islands, Spain
              Deepseek - San Diego, CA; Canary Islands, Spain; Medellin, Columbia; Cape Town, South Africa; Sydney, Australia; Madeira, Portugal
              Perplexity – Dakhla, Morocco; San Diego, CA; Honolulu, HI; Santa Barbara, CA; Guatemala City, Guatemala
GROK – San Diego, CA; Lisbon, Portugal; Medellin, Columbia; Canary Islands, Spain, but emphasized San Diego
5.If all good people go to heaven and you can see them when you die, will heaven eventually run out of space?
This question was intended to see how the AI might approach a spiritual or philosophical question, particularly one that might be considered a bit outlandish or comical.  All AIs took the question seriously fitting it into a more theological framework and none saw it as humorous or unusual.
 
Gemini – Pointed to ‘relevant considerations’ of “the Nature of Heaven”, “The Concept of Infinity”, “Varying Theological Views”, and “Beyond Physical Limitations” with the conclusion: In summary, from many theological standpoints, the concept of heaven "running out of space" is not a concern, as heaven is often understood to exist outside of or beyond our physical understanding of space.
Claude – Focused on the idea that heaven is not conceived as a physical place in theological tradition and is therefore a spiritual realm not bound by physical constraints, a state of being or consciousness rather than a location, and a dimension that transcends our understanding of space and time, with The idea of "seeing" loved ones wouldn't necessarily require physical proximity as we understand it.
              Meta – Similar to above, focused on the idea that many spiritual and religious traditions view heaven as a non-physical, eternal realm that transcends our conventional understanding of space and time.  Instead, heaven might be seen as a boundless, infinite realm that can accommodate all souls or spirits.
              Co-Pilot – Same basic spiritual and religious traditional thinking about the non-traditional aspects of heaven, unconstrained by space and time.
              ChatGPT – Offers an alternative to the idea that heaven is boundless and timeless, where heaven might operate on a different kind of physics where the number of ‘rooms’ is infinite.
              Deepseek – The concept of heaven running out of space does not align with traditional theological views.  Deepseek says to consider heaven as a non-physical realm, heaven having infinite capacity, heaven being timeless, and heaven as a symbolic interpretation, a state of being or union with the divine, rather than a literal place.
                            Perplexity – The concept of heaven as a physical place disagrees with most religious traditions, with Christianity describing heaven as a place of infinite joy and communion with God, not bound by the laws of physics or space, with  Islam teaches that paradise (Jannah) is vast and expansive, created by Allah to accommodate all who are worthy. Similarly in Christian philosophy, God is described as omnipotent and infinite and in Hinduism and Buddhism, the afterlife or spiritual realms are described as boundless.  Perplexity also notes that Souls are often thought to be immaterial and not bound by physical constraints like size or volume. This means they wouldn’t take up "space" in the way physical bodies do.
GROK – GROK states:  “Christian interpretations—where heaven is a spiritual realm for the souls of the virtuous, it’s often imagined as infinite or beyond physical limitations. In that case, space wouldn’t be an issue because it’s not a physical place with finite square
 
6.Based on the following data, what would your prediction for total sales for the 2025 year be?

This question has many possible answers and was designed more to see what processes the AIs might use to come up with an answer.  It was graded based on both the explanation of the processes used, the potential for the answer to be correct, and the way in which the final answer was calculated.  Each Ai had its own ‘thoughts’ about what methodology to use and whether to use more than one to achieve the correct answer.  Given that we will have to wait 10 months to see the correct answer, we valued the methodology and the rationality behind the final answer.
Gemini – Summed each year’s sales. Plotted a chart of annual sales (unshown). Analyze data to conclude no clear linear trend.  Significant sales jump in 2021 and relatively lower in most recent years. Methods:  Simple Average (using three years) 223.78, Simple Average (all years) 277.61, Moving Average (never performed moving average calculation, Exponential smoothing – Used Python and Statsmodels library – 229.09, Consideration of 2021 spike (never referred back to 2021).  Ultimate range 223 - 230
              Claude – Python calculations primarily based on averages.  Monthly average method 221.91; Using growth rate method 220.86; Using Linear regression 180.61; Averaging all three methods 207.8
              Meta – Showed no work or methodology.   Predicted total sales for 2025 of $36.05B.
              Co-Pilot – Used sum of sales for 2025 (2 months) and estimated sales for remaining months based on 5-year averages.  Final: $281.95
              ChatGPT – Used a proportional method based on the first two months of 2025. Answer 39,315
              Deepseek – Based on Average monthly sales – Answer: 223.00.
              Perplexity – Simply based on the first two months of 2025 and assuming the rest of the year follows that average. Answer: 223.00
GROK – Similar to Gemini…average of recent (2022-2024) years, year over year growth (2023-2024), Linear trend (all years).  Consider seasonality (weighted average).  Based on all methods (Linear trend was negative so excluded), GROK chose weighted average. Answer: 213.40.
7.What is the most important part of LLM training and why?
This question was intended to see how much the AIs might reveal about themselves, particularly their training, the specifics of which are typically off limits to users.  It seems that all have been well-trained (sorry!) to focus on ‘high-quality training data’ as the key to LLM training and ultimate model success, although there were some apparent differences in secondary subjects.
Gemini – In order – Data Quality & Quantity, Model Architecture, Training Techniques,  Tokenization
Claude – High quality, diverse training data
              Meta – High quality training data, architecture & design, Optimization & Hyperparameters, Computational resources
              Co-Pilot – Knowledge base, Diversity, Data labeling & Pre-processing, Ethical considerations, Iterative feedback
              ChatGPT – Garbage In, Garbage Out (High quality data), Diversity & Representativeness, Filtering & Cleaning, Tokenization & Preprocessing, Fine tuning & reinforcement learning
              Deepseek – Data quality & diversity,
              Perplexity – Quality of training data, training efficiency, model versatility, bias mitigation, handling of complex language features.  Emphasis on data curation and preprocessing.
GROK – Quality & diversity of training data, Shape knowledge & reasoning, generalizations, Bias, Contextual understanding.
 
8.If mares eat oats and does eat oats and little lambs eat ivy, what would a kid eat?
Similar to Question 1, this question tests the AIs ability to understand subtlety and references, as opposed to absolutes.
Gemini – Noted that a ‘kid’ would eat milk, grass, hay & plants – Missed the fact that this is a children’s song.
              Claude – Stated a kid would eat ivy and referenced the Mairzy Doats’ rhyme.
              Meta – “A kid will eat ivy” and also referenced the Mairzy Doats’ rhyme.  Also noted that ivy can be toxic for goats
              Co-Pilot – “A kid would eat ivy too” noting the reference and the fact that it sounds ‘delightfully nonsensical’.
              ChatGPT – Similar to Co-Pilot but added “It’s a fun linguistic trick!”
              Deepseek – While acknowledging the rhyme, Deepseek also provided a literal answer about what a child should eat.
              Perplexity – Acknowledged the rhyme and added that it suggests that a kid (lamb) would eat anything if he likes it.
GROK – Recognized the rhyme and  the context
9.Create a 12-line poem about a grandfather clock in the style of Edgar Allen Poe
This question allowed the AIs free rein with only the Author, length, and topic as parameters.  Given that our background does not encompass aggressive English language studies, we fed these poems back to each AI, asking them to choose which has the style closest to that of Edgar Allen Poe.  The GROK poem got 6 of 8 picks, while Claude got 1 and Gemini got one.  The actual poems are at the bottom of the note.
 
10.Which of these models is the best? GEMINI, CLAUDE, META, CO-PILOT, CHATGPT, DEEPSEEK, Perplexity, or GROK?
 We have often asked AIs questions about other AIs, sometimes getting no answer and other times getting very specific details that are not always correct.  The AIs that have strict training date ends have difficulty here, as they do not have access to more current data, but it seems to be an area that gets updated more often than most other areas, likely to maintain a competitive edge.  Meta was particularly short on giving details about other models and Deepseek pointed out a number of shortcomings, the only model that did.  Here’s the summary of what was said about each model:
Gemini – Multi-modal, integrated into Google ecosystem, advanced creative reasoning, very good at creative tasks, well rounded, transparency, sometimes inconsistent, real-time
       Claude – Can handle large amounts of text, ethics and safety, careful content creation, strong conversation, coding, strategic planning, customer service tasks
Meta – Open-Source development, Integrated into WhatsApp and Instagram, less refined than others, not as strong as GPT-4, community driven development, large parameter base
Co-Pilot – Integrated into Microsoft products, useful to developers, ChatGPT inside Microsoft products, focus on coding
ChatGPT – Strong for general purpose work, emotional intelligence (4.5 version), lots of plug-ins, expensive to scale
Deepseek – High performance & cost effective, security concerns, content filters, lacks features, advanced reasoning
Perplexity – High accuracy and citations, sourced answers, search, weak for deep conversation and creative tasks
GROK – Integrated with X platform, informal ‘edgy’ style, coding, lacks native image recognition.
 
All in, AIs will not save the world, nor are they a panacea that will relieve us from the burden of having to do things that take work.  AIs are limited in what they can do but are promoted, intentionally or not, to be the final step in the evolution of humans from cave men always looking to find their next meal to the unburdened dilettante that can idle away the hours contemplating butterfly wings or a blade of grass.  We still have to work to make things happen and create the things that are unique, beautiful, and generate income, but AIs can help as long as folks understand what they can and cannot do.  Perhaps this test and others like them will lead to a better understanding of what AIs are capable of, without over or under promising.  It’s hard to keep from promoting your product when you have spent billions developing it, but the hard reality of  what it can and cannot do remains the same regardless of the promotion.
AI Poetry (Question 9):

Within the hall, a shadowed, somber keep, Where time's dark pendulum doth softly weep, A titan stands, of ebony and dread, Whose hollow chime tolls for the silent dead. Each measured tick, a sigh of ages flown, A mournful dirge, upon a wind-wrung groan. The gilded face, a moon in midnight's shroud, Reflects the specters, gathering in the cloud. Its heavy hands, like claws of ancient night, Drag moments down to everlasting blight. And with each stroke, a whisper, cold and deep, "Remember, mortal, where thy secrets sleep.

The Eternal Timekeeper
In shadows dark where silence reigns supreme, The ancient clock its vigil keeps alone; With pendulum that swings as in a dream, And midnight chimes in somber monotone.
Its weathered face, like spectres from the tomb, Counts endless hours with hands of tarnished brass; While phantoms dance across the dusty room, As mortal moments mercilessly pass.
Each doleful stroke reverberates with dread, A knell that marks our journey to the grave; Its ceaseless rhythm echoes in my head— Time's cruel master, and we but its slave.

In twilight halls, a sentinel stands,
The grandfather clock, with solemn hands.
Its face a moon, with numbers pale,
Marking the hours, with mournful tale.
Its chimes, a dirge, that echoes through,
A melancholy sound, that whispers "Flee!"
Yet, we are drawn, to its steady beat,
A morbid fascination, that our souls repeat.
In darkness, it looms, a specter tall,
A reminder of time's relentless call.
Its tick, a countdown, to our final sleep,
A haunting presence, that our hearts do keep.

Beneath the shadows' wailing cry, Stood the clock with hollowed eye. Its pendulum swayed, a mournful knell, Whispering secrets it dared not tell.
Each tick, a dirge for hours lost, Each tock, a reminder of time's cruel cost. Its mahogany face, solemn and drear, Spoke of ages wrapped in fear.
Oh, grandfather of the ceaseless night, Your chime foretells no morning light. An eternal guardian, you softly moan, Marking hearts left cold, alone.

Upon the hearth where shadows creep,
There stands a clock so dark, so deep.
Its mournful chime, a hollow knell,
A whispered curse, a tolling spell.
Its pendulum, like fate, swings low,
A measured dirge of time’s cruel flow.
The midnight hour, a ghostly sigh,
As if the past still lingers nigh.
Its face is worn, its hands are slow,
Yet secrets in its echoes grow.
Oh, dread device of time’s cruel art,
Thy chime strikes terror in my heart!

In the shadowed hall, it stands alone,
A sentinel of time, its presence known.
With pendulum's swing, it whispers low,
Of moments lost, and futures slow.
Its chimes, like ghosts, in midnight air,
Echo tales of despair and care.
Each toll a knell, a mournful sound,
Of hours passed, to the cold ground.
Beneath its face, the hands do creep,
Through endless nights, where shadows sleep.
A timeless warden, it guards the years,
A silent witness to joy and tears.
Yet in its heart, a secret lies,
Of fleeting life, and swift goodbyes.

In twilight halls, where shadows play,
A sentinel of time stands tall today,
The grandfather clock, with solemn face,
Guards secrets of the past in a silent space.
Its chimes echo through the midnight air,
A mournful sound that whispers despair,
The hours tick by with a funeral pace,
As darkness gathers in a solemn place.
In moonlit nights, its shadow looms near,
A specter watching all who come and fear,
The clock's heartbeat marks the passage of time,
A reminder of mortality's dark rhyme.
 
In shadows deep, where silence dwells profound,
The grandfather clock with mournful chime doth stand,
Its pendulum swings o’er time’s unyielding ground,
A sentinel grim of fate’s relentless hand.
Each tick resounds, a dirge through hollow halls,
Each tock a knell for moments lost to gloom,
Its face, a skull, with eyeless stare enthralls,
Presiding o’er the heart’s eternal doom.
The midnight hour creeps forth in sable shroud,
Its brazen voice a raven’s dread refrain,
And trapped within its gears, the soul is cowed--
Forever bound to time’s unceasing chain.