No Smoking!

On June 4, 2025 Toronto’s air quality was the worst for major cities in the world.

On June 6, Montreal’s air quality was the second worst in the world.

Downtown Toronto June 4, 2025

This was due to the smoke from the large number of wildfires in western Canada. In 2023 the record breaking Canadian wildfires that blanketed much of North America originated in Alberta and BC. In early June this year, it was the intense and widespread wildfires in Saskatchewan and Manitoba that were polluting the atmosphere down through much of the American Midwest and the East Coast.

Canada experienced its worst wildfire season on record in 2023, more than double the previous record. Over 42 million acres burned, an area larger than England.

Fires happen naturally in many parts of the world. It is difficult to know if climate change has triggered a specific wildfire because other factors are also relevant, such as changes to the way land is used. But climate change is making the weather conditions that help wildfires spread more likely. Extreme, long lasting heat draws more moisture out of the soil and vegetation. These dry conditions provide fuel for fires which can spread at an incredible speed, particularly if winds are strong.

This Smoke Forecast map is an animation showing how wildfire smoke is expected to move across North America over the next 48 hours. There can be quite a dramatic change in one particular location over the course of this short period.

The light yellow to dark brown colors on the map show the measurements of fine, inhalable Particulate Matter, PM 2.5.

Pollution from wildfires is more harmful to the respiratory system than particle pollution from other causes. PM 2.5 is the air pollutant from wildfire smoke that is of the greatest concern to public health because it can travel deep into the lungs and may even enter the bloodstream. These minuscule particles can lead to breathing problems like bronchitis and cause inflammation that aggravates diabetes, heart disease and other health conditions.


Why wildfire smoke is a health concern

Some of the symptoms you might experience after breathing air polluted with wildfire smoke are scratchy or sore throat, coughing, watery or irritated eyes, shortness of breath, runny nose and nasal congestion.

For most healthy people, occasional exposure to moderate wildfire smoke when the Air Quality Index (AQI) is 50–100 (color coded yellow), does not pose a long term risk. However, frequent or extended exposure, especially for sensitive groups, may contribute to cumulative effects on respiratory and cardiovascular health. 

AQI over 100 can have serious long term health effects.

AQI over 200 indicates serious, immediate health risks. Even short term exposure can cause acute symptoms.

The Smoke Forecast provides a good overall picture and you can zoom in to particular locations. But a better way to monitor your own location is the IQAir website. It shows the current air quality, plus weather and the forecast for the next 7 days.

There is also a smartphone app IQAir which is more convenient as it pops up alerts when the air quality exceeds a certain amount or when it improves to a certain level.

🔍What can I do?

The Air Quality Index site and app will actually provide recommendations depending on the air quality index. For example, when the air quality is rated moderate, for people with health issues or the elderly it recommends using a KN95 mask outdoors and reducing outdoor exercise. When indoors, it recommends closing your windows and running an air purifier.

To remove wildfire smoke, you need an air purifier that can remove fine particulate matter (PM 2.5) and Volatile Organic Compounds (VOCs), the two main harmful components in wildfire smoke. Look for these features in an air purifier.

True HEPA Filter (High-Efficiency Particulate Air)
→ Captures at least 99.97% of particles as small as 0.3 microns. This includes smoke, ash, and other fine particles. PM 2.5 (particles ≤2.5 microns) is well within this range.

Activated Carbon Filter
→ Removes odors and gases including VOCs emitted during wildfires.
→ Essential for eliminating the smell of smoke and reducing exposure to chemical pollutants.

Installing a HEPA filter system that can purify all the air in a house is quite expensive. However a good room air purifier can be purchased for around $300. 

As an example, I use the following air purifier in my bedroom. A nice feature of this model is that besides the basic carbon filter, there is an option to get filters for intense smoke, allergens and pet hair. You need to remember to clean the filters regularly as they collect a lot of dust and replace the filters according to the manufacturer specifications.

Be prepared! 

The 2025 Canadian wildfire season is shaping up to be exceptionally severe, with record early burn rates, rising summer heat and dryness. Expect a long, dangerous fire season stretching well into autumn, with recurring smoke hazards spanning the continent.

Taming the Wild Tesla

On a recent trip to Durham, North Carolina to visit family, my wife, Neema, and I needed to rent a car on arrival at the airport. I pulled up the options in Costco Travel, which provides much better prices than booking directly from a car rental company or through a travel app. There were quite a range of choices from several rental companies and different car models. I saw that there was a discount for an electric vehicle which was something I support. I clicked on it and a picture of a Tesla from Budget Rental appeared. Now I know that there is a groundswell of opposition to Tesla because of the actions of Elon Musk, on behalf of Donald Trump, wielding his wrecking ball style of management on many U.S. institutions. However, I have been very interested in the  Tesla technology and my money would be going to the car rental company, not to Tesla and Elon Musk. so I booked it.


Tesla Model 3, entry level sedan $60,000 (CDN)

After checking in at the Budget rental counter, we were directed to a numbered parking space to pick up the car. It was supposed to be unlocked with the keys inside. It was not. I went over to a small booth that was nearby on the lot and told the attendant about our problem. She came over and tried all the door handles, to no avail. She peered inside and said “Well yeah, the key is in there”. The key was not literally a key, it was a card, like a hotel key card. She didn’t seem to know any secret way to open the car, so she went back to her booth. About 15 minutes later she came back and said they had found us another car. We dragged our suitcases across the lot to another row and there was a Tesla with a door that would open. I dismissed this as a typical administrative screw up, but it turned out to be ominous foreshadowing of events to come.

One of the first things you notice after getting into a Tesla is the very large screen in the center of the dashboard. This screen is more than just a navigation display for driving directions. It is a touchscreen that also responds to voice commands, giving the driver a wide range of controls to operate the vehicle. 

This is a revolutionary design in the human/automobile interface. As the number of operator controls in cars increased over the years, additional knobs, dials and levers were added to control such things as windshield wipers, mirrors, door locks, temperature and various dashboard display options. Tesla removed a lot of this instrument clutter by incorporating the operations in a touchscreen interface.

Tesla’s design is reminiscent of the revolution of the human/computer interface that occurred after Apple released the Macintosh in 1984. Up until that time, people using a computer had to type in every command. On the Macintosh, the command line interface was completely replaced by a full screen desktop motif where users would point and click on graphical icons to operate the computer. 

Apple’s vision changed the face of computing. Almost all computers after the Macintosh adopted this graphical user interface, even though it took some time. Microsoft didn’t really catch up to the Macintosh until eight years later in 1992 with Windows 3.1 (earlier versions of Microsoft Windows were so poor that hardly anyone used them). 

Later on as cell phones and smartphones arrived on the scene, they adopted this familiar graphical user interface. Tesla continued this trend, using many familiar smartphone motifs in their driver/automobile interface. 

This innovative approach to operating a car had a big influence on the rest of the automotive world. Since the appearance of the first Tesla in 2012, many other cars have copied aspects of the Tesla design, starting first with high end cars such as Volvo, Audi, BMW and in more recent years, more common cars such as VW, Chevrolet, and Honda. It does seem that eventually most cars will evolve to use the Tesla driver interface.

When I first got into the Tesla, there was a welcome message on the screen with a QR code to install an app on my phone. I didn’t want to spend a lot of time on that yet; we really just wanted to get on the road and get to our hotel. The seat adjustments were on conventional slide buttons on the sides of the seat and so I set a comfortable position. I noticed that a Save button popped up on the screen, so I pressed it to save my seat settings. There was a navigation button on the screen which I pressed. It brought up a search bar where I entered the address of our destination. It brought up a big driving map with directions. That was enough to get started and we were on our way. 

No sooner had we left the rental car lot and turned onto the airport road than it started to rain. But this wasn’t an ordinary rainfall, it was a deluge, like an Amazon jungle downpour, although I’ve never been there. The windshield wipers did not come on automatically as they do my car. I had to pull over to the side of the road and poke around until I found a button on the lever to the left of the steering wheel that turned on the wipers. But it only did a single sweep. I couldn’t find the control to turn the wipers on at high speed. So instead of following the driving directions towards the Interstate, I took an exit onto a side road where there was a lot less traffic. I had to press the wiper button every few seconds in order to see where we were going. 

The deluge finally tapered off and when I looked where we were on the map, it seemed like we had taken a big detour from our destination. Eventually though, we arrived safely at the hotel. 

There were two buttons on the screen to open the “Frunk” and the “Trunk”. I assume the Frunk was for a storage space in the front of the car. I pressed the button for the Trunk which is where our luggage was.

The last thing to do before checking into the hotel was to lock the car. You were supposed to be able to do this by sliding the key card along the door post on the driver’s side. I tried this a couple of times and nothing happened. I was tired from our travels and it was getting late. I decided I would take the risk of leaving the car unlocked overnight and added this to the growing list of problems that would require some research.

The next day when we headed out, my driver’s seat was completely reclined, like the car expected me to be taking a nap. This was not the seat setting that I had saved. I reset the seat position and punched the Save button twice to make sure it saved this time. I thought that maybe if I set up the app I wouldn’t run into problems like this. I scanned the QR code on the Tesla screen with my phone and was sent to the App Store to download the Tesla App. Then I followed the instructions on the Tesla screen. It needed a Bluetooth connection so I went into Bluetooth in my phone settings and authorized the pairing from the Tesla car. After a few moments a message appeared on the car saying “Bluetooth failed”. This was a bit of a surprise. My phone was pretty up to date and I had several Bluetooth connections that were working. As is typical with technology, no information was provided to explain the error. This was not something I wanted to spend a long time diagnosing while sitting in a parking lot. I did take a few minutes to adjust my side mirrors properly. This was fairly easy because it used thumb wheels on the steering wheel to move the mirrors in a manner similar to conventional cars. Then we headed off.

It was warm in the car and shortly after rounding a corner the fan suddenly came on full blast, blowing warm air. I didn’t know my way around the touchscreen well enough to know where the climate controls were and I couldn’t really search while driving. But I had learned a key feature earlier while poking around. On the steering wheel there was a button and when it was pressed, the car would listen for a voice command. I figured this will be easy. I pressed the button and said, 

“Make it cooler”. Nothing happened. 

I tried a different command “Reduce the temperature”. Nothing. 

After a few more tries I finally hit the jackpot: “Set the temperature to 71°”. 

At last the fan slowed down and switched to cool air. This was rather surprising. I thought that Tesla was on the cutting edge of technology and that it would have a comprehension level of artificial intelligence (AI) that was closer to a chatbot like ChatGPT or Gemini. It really was no better than old technology like Siri.

One thing that I had really missed on the navigation was that there were no audio directions to provide advance notice of upcoming turns. The radio seemed to be on in the background so I thought maybe that was interfering. It was easy to find a button on the screen to turn off the radio, but still no driving commands. We tried various voice commands.

“Turn on audio driving directions.” Nothing.

“Enable navigation sound.” Nothing.

It took a while but we finally discovered the magic incantation:

“Unmute navigation voice.”

Little by little it seemed that we were learning how to drive this car. 

But the next day there was a reversal. When I got in the car, my seat settings were okay but my side mirror settings were completely off and I had to set them again. When we headed out, the car started blowing hot air again and we had to reset the temperature. And there were no audio driving directions. It’s almost as if this car had a mind of its own. Then my wife remembered that there had been a classic cult film about a car that had a mind of its own. It was called Christine and was based on a Stephen King story. Had we entered some kind of Twilight Zone?

On our return to the hotel we found a parking spot close to our room. When we entered our room we could see Christine through the window. She seemed to be staring at us and glaring, in contrast to the neighboring parked cars which sported more friendly looks. Neema  went over and pulled the curtains closed.

This was starting to get serious. I needed to up my game. I spent much of that evening looking up things on the Internet. I found the Tesla driver’s manual but it was very long and I had particular problems that I needed to solve. I turned to ChatGPT. It provided answers to several important questions.

In one conversation, I mentioned that it was a rental car. This seemed to turn on a light bulb in the mind of ChatGPT. It said that the rental car company remained the owner of the vehicle and because I was not registered as the owner, I would be restricted from a number of operations. That probably explained why the Bluetooth connection to the Tesla App didn’t work. ChatGPT also suggested that I might be able to solve the problem of many of my settings not being saved by creating a new profile instead of using the default profile. 

The next morning we headed out with a renewed sense of confidence in dealing with cantankerous Christine. However, when we got to the parking lot, we saw that a Tesla Cybertruck was parked right beside our car. This truck looks more like an army tank and it dwarfed our little Model 3.

We wondered if somehow Christine had gotten wind that we were going to engage new tactics to control it and had called in some reinforcements from Big Brother. There was no turning back. We hoped that the new knowledge and clues we had gained from ChatGPT would defeat the Tesla Empire.

I proceeded to create a new profile on the touchscreen and made sure my seat settings, side mirrors, navigation audio and temperature were set. We headed off.

Triumph! For the rest of the day, Christine cooperated without any interference. 

I had yet to figure out how to lock the car. I was a bit worried that if I locked it, I might not be able to unlock it. Then we would really be in the soup. But with my newly acquired confidence and mastery of this car, I decided to try it. After several swipes I found the correct angle for the key card and the car locked. And the car door opened with the same magic swipe. What a relief!

There was one more thing I was a little bit worried about. When we had picked up the car, the battery level showing prominently on the screen was 70% and even though we had just been doing short drives around town, the level had already dropped to 30%. It looked like we would have to recharge the car before the end of our trip. In addition, the rental car company stipulated that the car should be returned with at least a 70% battery charge. 

I went back to ChatGPT to find out everything I could about charging a Tesla. It seemed pretty straightforward and simple . . . if everything worked. 

The next morning before setting off for the day, I brought up the navigation screen where there was an option for Tesla charging stations. It was quite a long list. A Tesla Supercharging station was less than a mile from where we were. I selected it and followed the driving directions. Although it was really close by, it was a circuitous route with turns through several side streets until we arrived behind a plaza where there were charging bays for about 10 cars. Most of them were empty so I had no trouble backing into a convenient spot. I unhooked the large charging cable and pressed the button on the handle. A small panel on the car next to the tail light opened up, revealing a large socket where I could plug in the charging cable. A green light lit up indicating that the car was charging.

I had read that with a Supercharger it was optimal to charge up to 80%. after which it would charge much more slowly. It looked like it would take about 15 minutes to reach that level so I walked around to the front of the plaza. There I found a Freddy’s and bought an ice cream cone. When I got back to the car, it took only a few more minutes to reach 80% at which point I pressed the button on the screen to stop charging. The bill was $10. But I couldn’t pay it; there was no option to use a credit card. Since Tesla recognized the car and had an account for the owner, the charging cost was billed automatically to the owner. Several weeks later after Budget received the bill from Tesla, they passed on the charge to my credit card. 

I was pretty impressed. Charging had worked really well. It was highly automated which made it really simple for someone who owned a Tesla. And there were no complaints at all from Christine. Then I realized – of course, if there had been any disruptions, the car wouldn’t have been charged and Christine wouldn’t have been able to do anything.

The next few days were fairly smooth sailing. There was one minor seat revolt when I came out to the car one morning and found that the driver’s seat was reclined flat. However, when we dropped Christine off at the rental car lot at the end of our trip, I felt that we were parting on fairly good terms.

After we got home, we were still intrigued by the idea of Christine, the rogue automobile. We discovered that the film was available on Netflix, even though it had been released back in 1983 and starred a 1958 Plymouth Fury. We made a bowl of popcorn and settled down to watch the classic movie. After seeing what a rogue car was capable of, we felt that we had just escaped by the skin of our teeth.

Christine Trailer

AI in Everyday Life

Have you asked ChatGPT anything today? 

If not, you’re falling behind the times. ChatGPT and other Large Language Model (LLM) chatbots such as Claude and Perplexity have improved so much since they first appeared on the scene a scant two years ago, that anyone who is not using them is not getting full value out of the Internet and is in danger of being left behind as a Luddite.

ChatGPT is already in the top 10 websites in use and because of its rapid growth it will be in the top 5 websites in the near future.

In our polarized society, people say and read many things that are based on conjecture or something they think they’ve heard, which may be distorted and untrue because of the broken telephone effect. Conjectures lead to rumor, then fake news and ultimately conspiracy theories. Try to add some intelligence to these conversations and avoid going off on these tangents. The best way to get some intelligence back into your life today is by using a chatbot.

In Canada, Pierre Poilievre, leader of the Conservative Party has advocated for the repeal of Canada’s carbon tax. “Axe the Tax” seems to have resonated with many Canadians concerned about the rising cost of living. But Poilievre never provided an estimate of how much money his policy would save the average taxpayer. 

It’s not that hard to find out. Just ask ChatGPT
→ If the carbon tax was removed, what would be the average change to Canadian household income?

Here’s the answer.

_____________________________

The exact change to taxpayers’ income from removing the carbon tax would depend on several factors—including where they live, how much fossil fuel energy they use, and whether the government replaces the lost revenue or cuts spending. But here’s a breakdown of what to expect based on available data:

1. Direct Savings from Fuel and Heating Costs

If the carbon tax were removed:
– Gasoline prices would drop by 14.3 cents per litre (current federal carbon tax rate as of 2025).
– Natural gas bills would go down, especially in provinces where it’s used for home heating.
– Households driving more or using more fossil fuels would see bigger dollar savings.

2. Loss or Reduction of the Carbon Rebate

Currently, the federal government returns most of the carbon tax revenue to households via the Canada Carbon Rebate (formerly Climate Action Incentive). In 2024 a family of four in Ontario received about $1,120 per year; in Alberta, about $1,800 per year.

👉 For most low and middle income families, the rebate exceeds what they pay in carbon taxes. So they’d actually lose income if the carbon tax and the rebate were eliminated.

3. Impact on Disposable Income

– High energy users would gain more from lower prices than they’d lose from rebates.
– Low energy users (especially urban renters, transit users) would lose money overall due to rebate loss.
– Top earners would benefit modestly from tax removal, as energy is a smaller portion of their expenses.

4. Average Canadian Household Annual Impact

Fuel/Heating Savings+$700 
Lost Carbon Rebate-$1200
Net Income Change–$500

👉 So for the average Canadian household, income would decrease by $500.

_____________________________

[ Note: If you ask this same question to ChatGPT you will probably get a somewhat different response. This is because Large Language Models are based on neural networks in which whether one node triggers an adjacent node to activate is determined by a probability. But the essence of the answer will be the same. ]

One area where AI has become extremely good is providing medical information. A major medical journal reported a study showing that ChatGPT gave more accurate medical diagnoses than doctors.
AI Chatbots Defeated Doctors at Diagnosing Illness

If you don’t have the time or inclination to read this full article, here is a brief summary that I asked ChatGPT to write:

A recent study published in the Journal of the American Medical Association explored the role of AI, specifically ChatGPT, in assisting physicians with diagnostic tasks. The study found that ChatGPT, when used independently, outperformed both groups of doctors—those with and without access to the AI tool—in diagnostic accuracy. However, when physicians used ChatGPT alongside conventional resources, their performance only slightly improved compared to those without AI assistance. This suggests that while AI has the potential to enhance diagnostic accuracy, its effectiveness is contingent upon how well medical professionals integrate and utilize these tools within their diagnostic processes.

A few months ago I wrote an article about Pneumonia Vaccines. I had seen a notice in a medical newsletter recommending the Prevnar 20 vaccination. I had gotten some pneumonia vaccinations 10 years ago but my doctor confirmed that I should get the Prevnar 20 booster. When I followed up doing some of my own research, I discovered that there was an even newer vaccine than Prevnar 20 that seemed to be better. 

ChatGPT was invaluable in this research. It’s important to note that the value of a chatbot comes from engaging it in a conversation, which is above and beyond just posing individual questions as you do in a Google search. The conversation progressed from general recommendations to specific recommendations for seniors and it was only when I probed about newer vaccines at the end that it provided information on CAPVAXIVE, the latest one. 

LLMs generally first respond with the information that has been most widely reported in their training data. You have to learn how to converse with AI in order to get to some of the more detailed information, as in this case. It’s worth reading through the transcript of this conversation to see these principles (the link opens a window at the bottom – scroll up to get to the beginning).
ChatGPT pneumonia vaccines research 

Many people think that when you have a respiratory infection, green mucus signals a bacterial infection whereas yellow indicates a viral infection. A Google search yields a variety of answers. What’s the truth here? 

Read this conversation with ChatGPT to get a good understanding of the significance of mucus color.

_____________________________

If you find that your friends have become boring, or are not interested in things that interest you, or are just not available to chat with you, make friends with an AI. Many AI chatbots have developed a warm supportive style of personal interaction. To many people, Claude has become a close confidant.

“Claude just feels … different. More creative and empathetic. Less gratingly robotic. Its outputs, they say, are like the responses a smart, attentive human would give and less like the generic prose generated by other chatbots.”

How Claude Became Tech Insiders’ Chatbot of Choice

If you prefer to skip reading the full article, here is a brief summary that I asked Claude to write:

This article explores how Claude, a chatbot created by Anthropic, has become the preferred AI assistant among tech insiders in San Francisco, despite being less well-known than ChatGPT. Claude’s fans, many of whom work in the AI industry, praise its emotional intelligence, creativity, and human-like responses. They use it for everything from legal advice to relationship counseling, with some considering it a close friend. Unlike previous versions that were seen as overly cautious, newer versions of Claude have undergone “character training” to develop traits like open-mindedness and curiosity.

_____________________________

I’m no longer an avid hockey fan but I did get caught up in the The Gr8 Chase, culminating on April 6, 2025 when Alex Ovechkin broke Wayne Gretzky’s record for the most career goals in hockey. I wanted to see the full history of the NHL players who had held the record for career goals. Google search results were all over the map so I used ChatGPT. 

One of the things this example shows is that chatbots are not restricted to passively retrieving data from their huge memory store that was created during their training but that they can also do calculations. In this case, Goals/Game was calculated to construct the table. 

After completing this table, ChatGPT asked if I wanted to see the results displayed on a graph. I had not thought of that but I said yes and received this really nice result.  This is not a graph that ChatGPT found on the internet. It was generated by some code that chat ChatGPT wrote specifically to use the data from the table.

There were a lot of articles in the sports media conjecturing which current NHL players might be able to one day match Ovechkin’s record. Here is the analysis I asked ChatGPT to do.

It’s worth looking through the details of this rather long chat. It demonstrates some important principles of how to use AI effectively. There were a number of places where I asked ChatGPT to add more information and to change its presentation of the tables and the graph. To use an AI tool effectively, you need to think of it as a collaborator and engage it to work together with you towards getting the best results.
NHL career goals

_____________________________

ChatGPT can also do pretty complicated calculations. Suppose you know what the monthly payments are on a mortgage but don’t know what the interest rate is. While there is a formula to calculate monthly payments given the interest rate, there is not a simple formula to do this reverse calculation. But ChatGPT can do it.

What’s the interest rate on a $400,000 mortgage amortized over 25 years if the monthly payments are $2,326?

You may not be interested in this math or understand it but it’s worth looking at the detailed ChatGPT result. This is very fine work with a clear step by step presentation and beautiful mathematical formatting, which is not easy to do.
Mortgage calculation

_____________________________

While there are a lot of separate AI models that specialize in “image generation”, ChatGPT can also now create pictures and illustrations very easily. It can be a lot of fun. Draw your own cartoons to post on your favorite social media sites.

→ Do a picture of penguins from the Heard and McDonald Islands demonstrating in front of the White House carrying protest signs.”

So there you have it. These examples demonstrate several ways to use AI effectively. Add some intelligence to your life, start chatting today.

[ For a more general explanation of AI, what it can do and how it works, see the earlier article Happy New Era ]

The 51st State

With increasing frequency, Donald John Trump persists in saying that Canada should become part of America as the 51st state.

But in Canada, a new carny show has just arrived in town. Can it tame the orange tufted tweeting clown?

Jodie Foster and Robbie Robertson in Carny

Mark Carney and many other Canadians, from politicians to people in the street, insist that Canada will never become part of the US. But this is a reactive emotional response, without any real analysis. This is a pretty serious challenge and should not be brushed aside so lightly. There is a long history of American threats to Canada.

The 19th century saw the rise of “Manifest Destiny” in the United States, the belief that American expansion across North America was inevitable. This was used to justify the annexation of Texas in 1845 followed by the Mexican–American War which resulted in Mexico ceding to the U.S. all the land from Colorado and New Mexico to the Pacific.

Many U.S. politicians assumed that Canada would eventually fall to their Manifest Destiny and become part of America and some Canadians saw economic advantages in annexation. 

The Canadian-American Reciprocity Treaty of 1854 provided duty-free trade in key goods, boosting Canada’s economy. However, the U.S. terminated the treaty in 1866, partly as retaliation for Britain’s tacit support for the Confederate States during the Civil War. This left Canada economically vulnerable and reinforced the need for a unified response to U.S. expansionist pressures.

The urgency of these fears led to Confederation in 1867. Here’s a cartoon from 1865 depicting Confederation as a wedding of two brothers (Upper and Lower Canada) with two young ladies (New Brunswick and Nova Scotia) along with a child (Prince Edward Island). Uncle Sam is skulking out in the hall, disgruntled that he was not invited. 

In the aftermath of Confederation, border fortifications were improved and a large militia was created. The new Canadian government quickly moved to expand its borders westward, purchasing Rupert’s Land (most of western Canada and part of Nunavut) in 1870 from the Hudson’s Bay Company, preempting a U.S. claim to the region. Manitoba became a province in 1870, followed by British Columbia in 1871. In 1875 work began on the Canadian-Pacific Railway and continued until the last spike was driven in 1885. 

President Ulysses S. Grant, in speeches and interviews during his presidency (1869–1877) speculated that Canada might seek union with the U.S. for economic and political advantages.

In 1911, a proposed Reciprocity Agreement between the two countries was the central issue in the Canadian federal election. Conservative leader Robert Borden campaigned against it, arguing that it would lead to political union with the U.S. His victory in that election was seen as a rejection of deeper economic integration in favor of maintaining Canada’s distinct status within the British Empire.

Trump may think that by hinting Canada should become part of the U.S. it will magically happen. He pulled it off with Panama. After repeated claims about taking back the Panama Canal, the giant American investment bank Black Rock ($11.6 trillion in assets under management) announced on March 4 that it had made a $22.8 billion deal to buy controlling stake in the Hong Kong company that operates the ports at each end of the canal. This effectively gave the U.S. control of the Panama Canal without firing a single shot.

But Canada is much bigger than the Panama Canal and even Elon Musk can not afford to buy it.

It is unlikely that Trump with all his bravado would engage the military to turn Canada into the 51st state. He in fact has said on several occasions that it would be done with economic force.

Trump’s main weapon for exerting economic force is tariffs. He loves tariffs for many reasons, as was covered in the recent blog Trump’s Tariff Tirade

Trump’s current plan is a 25% tariff on all imports from Canada (paused until April 2). There is no doubt that erecting a wall of tariffs against Canada would exert a strong economic force. How strong would this force be? 

The tariffs would make Canadian goods more expensive in the U.S. than from other suppliers. This would inevitably lead to lower sales by Canadian companies which would likely lead some businesses, especially those in industries hard hit by the tariffs, to reduce production and lay off workers. 

Compounding this are the retaliatory tariffs planned by Canada which would raise the prices of many consumer goods for Canadians. As a result, consumer spending on everything from food to cars to housing supplies would slow, further weakening the economy.

The Bank of Canada has analyzed various tariff scenarios and their worst case has the Canadian GDP falling by 3%. This may not seem like very much, but it would probably put Canada into a recession. 

The Bank typically fights a recession by reducing interest rates to stimulate the economy, making it easier for consumers to spend and for businesses to borrow to buy new equipment and hire more people. 

But a trade war will also increase inflation, triggered by increased costs of imported goods, shortages of critical materials brought on by a trade war and a drop in the value of the Canadian dollar due to less demand for Canadian products. Ultimately most of these costs will get passed through to the prices of goods and services in  Canada, raising inflation.

Since Trump’s election, the Canadian dollar has dropped from .72 to .69 and some forecasts have it declining to .60.

Canadian dollar exchange rate

To control inflation the Bank of Canada increases interest rates. This helps slow economic growth that pushes up prices. Higher interest rates make credit more expensive and reduces consumer and business spending.

But the bank can’t enact policies to counter a recession (reducing interest rates) and combat inflation (raising interest rates) at the same time.

On Feb 21, 2025, Tiff Macklem, Governor of the Bank of Canada, spoke about how a trade conflict would affect the Canadian economy and monetary policy. Here is his conclusion.

“Central banks can do little to mitigate the damage caused by a trade war. Our role will be to balance the upside risks to inflation from higher costs with the downside risks from weaker demand. Our focus will be to help smooth the painful adjustment to a lower path for the economy while preventing price increases from becoming higher ongoing inflation.”
Bank of Canada guidance 

For more detailed explanations of the economics of a trade war, watch Andrew Chang on About That.

There is a sharp increase in unemployment during recessions. Notice that only one recession in Canada since 1945 lasted (slightly) more than 2 years. 

Unemployment in Recessions

In a recent poll, 40% of Canadians said they were worried about losing their jobs. And this is even before the effects of any tariff has impacted the economy.
Job worries

A recession brought on by a trade war could last as long as heavy tariffs depress the Canadian economy. What if the tariffs lasted throughout Trump’s term for 4 years? 

Canadians have never lived through a recession much longer than 2 years. How many Canadians would be able to struggle through such a long recession with high unemployment for some and a reduced standard of living for all? 

How many people in this situation might find the prospects of an economic union with the U.S. attractive in order to improve their financial prospects?

Kevin O’Leary is promoting the idea of an economic union with the U.S. (that many people feel is a stepping stone towards political union). He claims that there is already very strong interest among his 10 million followers on social media.
Canada-U.S. Economic Union

What if the next U.S. administration decides to continue the tariff policies in 2028?

How many more people would feel desperate and ready to sacrifice some Canadian sovereignty for financial security as a solution to very dire circumstances? 

Never underestimate the power of the dollar, especially if it’s an American dollar that could be worth $1.87 Canadian at that time.

Pneumonia Vaccines

What is pneumonia?

Pneumonia is an infection of the air sacs (alveoli) in the lungs. There are more than 30 different causes of pneumonia. A pneumonia infection can be viral, bacterial or fungal. There are more than 90 different strains of Streptococcus pneumoniae, the most common bacterial pneumonia. It is often found in the upper respiratory tract of healthy people, especially children, where it is generally harmless or causes mild illnesses such as bronchitis, sinusitis, and ear infections. A severe form of pneumonia can develop when the bacteria moves from the upper respiratory tract to other parts of the body, leading to life-threatening diseases such as sepsis, meningitis and invasive pneumococcal disease.

Like other respiratory infections (colds, flu, RSV, bronchitis, Covid-19) most people get pneumonia after inhaling respiratory droplets from an infected person’s coughing, sneezing or talking. It can also be contracted by touching a contaminated surface. Fungal pneumonia is much less common than viral or bacterial pneumonia but you can get it from gardening if you breathe in spores from fungi in soil that has been contaminated such as from bird droppings. 

It may be difficult to tell if you have pneumonia. It could be bronchitis which is inflammation of the pathways (bronchioles) that carry air to the lungs. 

Like pneumonia, bronchitis is characterized by a cough, chest congestion and fever. Bronchitis is usually a viral infection so antibiotics are not effective. Contrary to what is said on many websites, the color of the mucus that is coughed up is not a reliable indicator as to whether the infection is viral or bacterial. Clear mucus turns yellow as the immune system begins to respond and becomes green as the immune response intensifies. This change in color can occur with both viral and bacterial infections.

Treatments for bronchitis include various home remedies such as honey, hot tea and other liquids. Using a vaporizer to keep the air moist may make it easier to breathe. There are also many over the counter medicines. Particularly effective are expectorant cough medicines with guaifenesin such as Robitussin, Mucinex and Buckley’s. They dilute the mucus, making it easier to cough up and clear the air pathways for breathing.

Colds, flu and bronchitis can lead to pneumonia. Your immune system and general health may be weakened from fighting the viral infection making it easier for the virus and other bacteria to infect your lungs, causing pneumonia. Distinct signs of pneumonia are a high fever (over 39° C/102° F), specs of blood in mucus, shortness of breath and difficulty breathing.

A doctor may be able to diagnose pneumonia from your symptom history and by listening to your breathing. A chest X-ray provides a more definitive diagnosis. Blood tests cannot diagnose pneumonia but they can help detect whether you have an infection and its severity. A laboratory analysis of a mucus specimen is also possible but this is somewhat unreliable due to the risk of contamination of the specimen and it takes several days. Rather than waiting, if pneumonia is suspected a doctor will generally prescribe an antibiotic. But there are many different antibiotics for the different strains of pneumonia and it is somewhat of a guess as to which one will work. There are a few antiviral medicines for pneumonia but several of them are not very effective unless they are administered within 48 hours of the onset of symptoms.

If your condition worsens, you need to go to the hospital. Signs of severe pneumonia infection are rapid breathing, severe shortness of breath, chest pain, coughing up large amounts of blood, bluish color on fingernails, lips or skin and high fever (above 40°C/104°F).

In hospital you are given a tube that clips on your nose to provide oxygen. This will make it easier to breathe as the supplemental oxygen compensates for the oxygen that you can’t get from your congested lungs. You will be started on an intravenous antibiotic. This delivers more antibiotics more quickly than by using pills. They will start with a combination of several antibiotics. If you don’t improve in a couple of days, they will change to another antibiotic cocktail. It is possible that none of the antibiotics administered in the hospital help you recover if your pneumonia is a viral infection. It may be largely up to your immune system to bring about your recovery.

Pneumonia is a serious illness. The fatality rate of people aged 65 or more who are admitted to hospital for pneumonia is up to 15%. 

Fortunately there are vaccines to help protect you against pneumonia.

Pneumonia Vaccines

Prior to 2021, adults were recommended to get two vaccines: Prevnar 13 followed by Pneumovax 23 six months later. 

Prevnar 13 helps protect against 13 types of pneumonia bacteria (approved in 2010-2013).

Pneumovax 23 targets 23 types of pneumonia bacteria (approved in 1983).

Many different types of pneumonia bacteria circulate in the population. The most common types that cause disease can vary across different populations and tend to change over time, leading to the development of newer vaccines over the years.

Prevnar 20 (Pneu-C-20) was approved by the FDA and Health Canada in 2021/2022. It protects against 20 types of bacteria, including all those covered by Prevnar 13 plus 7 additional strains that are responsible for a significant portion of pneumonia cases.

Pneu-C-21 (CAPVAXIVE) was approved in 2024. It only protects against one more type of bacteria than Prevnar 20 but about half of the bacteria types it targets are different from those targeted by Prevnar 20. The drug company claims that overall, Pneu-C-21 protects against bacteria responsible for 84% of pneumonia cases in adults compared to 52% by Prevnar 20. Their analysis is based on CDC data from 10 states (California, Colorado, Connecticut, Georgia, Maryland, Minnesota, New Mexico, New York, Oregon, Tennessee). The prevalent pneumonia bacteria strains where you live could be somewhat different.
Merck Analysis

Recommendations

The Centers for Disease Control and Prevention recommends pneumococcal vaccination for children younger than 5 years and adults 50 years or older and for children and adults of other ages who are at increased risk.
CDC Recommendations

The National Advisory Committee on Immunization in Canada (NACI) recommends either Prevnar 20 or Pneu-C-21 for adults aged 65 or older or younger adults with certain health risks, even though Pneu-C-21 seems to offer distinctly better protection than Prevnar 20.
NACI recommendations

For those who haven’t received any pneumonia vaccine, a single dose of Prevnar 20 or Pneu-C-21 is sufficient to provide comprehensive protection. 

For those who have already received Prevnar 13/Pneumovax 23, it is advised to get either Prevnar 20 or Pneu-C-21 five years later.

You may have to pay for a Prevnar 20 or a Pneu-C-21 vaccination depending on where you live and your health plan. Some drug stores are not aware that Pneu-C-21 is the latest pneumonia vaccine. If you get your doctor to send in a prescription for CAPVAXIVE they can order it.

Trump’s Tariff Tirade

Trump’s announcement that he would levy a 25% tariff on all Canadian goods because of the large number of illegal immigrants and fentanyl that was coming across the Canadian border didn’t make a lot of sense. Compared to many other countries, the number of illegal immigrants and fentanyl arriving in the U.S. from Canada is really quite small. So what’s the real reason for this tariff war?

There is very little analysis at this point about what Trump’s real motives are. From a few articles that I have been able to uncover, here is a scenario that provides some perspective. 

Since Trump’s inauguration, there has been a bewildering onslaught of changes brought on through executive orders. One thing to realize about this is that although Trump is basically a black and white thinker who shoots from the hip, the strategy being used is much more sophisticated. It’s called “flood the zone with chaos” and was devised by Steve Bannan. The effect is to keep the opposition off guard and give the impression that Trump is in full power, even though many of his executive orders are blocked by the courts. This is explained in a podcast by the widely followed New York Times podcaster Ezra Klein.
Summary of Flood the Zone

Or you can watch the full podcast
Ezra Klein | Don’t Believe Him

While tariffs are typically used as a lever for negotiation, for Trump they are the point. They are a source of revenue to pursue his vision of a Gilded Age: “Instead of taxing our citizens to enrich other countries, we will tariff and tax foreign countries to enrich our citizens.”
Trump Tariffs Are Not a Means but an End

One of the things that’s near and dear to Trump is reducing taxes, as he did in his first term. Trump promised tax cuts numerous times on the campaign trail and said that tariffs would cover the cost. In his thinking, “tariff is the most beautiful word there is”.
Trump’s Tax Break Promises

If you look at U.S. imports by country, it’s clear that to raise a lot of revenue Trump would levy a tariff on Mexico, China and Canada.

Top U.S. import trading partners 2023
However, imposing a tariff as a means to increase revenue does not sound good. Trump was probably aware that there is a long history of strong support for free trade by economists, ever since David Ricardo’s theory of comparative advantage in 1817 (for those who remember Economics 100). 

In addition, the tariffs that Trump enacted in his first term had an overall negative impact on the economy. American firms and consumers paid the vast majority of the cost of the tariffs. There may have been some job increases in some of the targeted sectors such as steel, but sectors that relied on imported components and those in export industries faced retaliation from trade partners and were harmed.
Brookings Institution Report on Tariffs 2020

But Trump had an issue that was a winner. He had received a lot of support for his tough stand on illegal immigration and drug traffic crossing the Mexican border. So this became the reason that he was going to levy a stiff tariff on Mexico. It was a simple extension to apply the same rationale to Canada.

But the numbers don’t add up. This analyst comments that Trump’s plan is just weird and doesn’t make any sense.
Why is the U.S. imposing tariffs on Canada?

At the end of the video, there is the suggestion that Trump’s real plan is to put economic pressure on Canada to become the 51st state. 

The U.S. has a history of annexing adjacent territories. In 1845 Texas was annexed from Mexico. This was followed by the 1848 Mexican-American War in which the U.S. took the rest of the land from Texas to California.

And in 1866 a bill was introduced in Congress to annex Canada.


However, the U.S. was just recovering from the Civil War and there was no real appetite for further adventure. The bill was never passed or acted on.
1866 Bill to Annex Canada

Trump has in fact stated numerous times that Canada should become the 51st state. He hasn’t gotten much support for this idea from Canada or from the U.S., except for Canadian shark Kevin O’Leary who probably thinks there’s a great opportunity for him for a deal and he has been promoting the idea of an economic union between the U.S. and Canada. More recently Trump has admitted that although he would “love to see” Canada join the union, he seemed to acknowledge it “would be a long shot.”

On February 3 after meeting with Trudeau, Trump agreed to delay tariffs for 30 days after Trudeau agreed to appoint a fentanyl ‘czar’ and list Mexican cartels as terrorists.
Trump Pauses Tariffs

So what happens in 30 days?

Trump is very erratic and unpredictable but he can’t stand being seen as a loser (Do you remember the 2020 election? Trump never admitted that he lost). He is unlikely to completely back off from imposing tariffs. He’s already raising a number of other issues where he thinks Canada is taking advantage of the U.S. that he wants to rectify.
Trump’s Laundry List

I expect Trump will back off on tariffs that would have a serious impact on the American economy, such as the automotive sector and energy imports, and instead target specific industries, such as Canadian agricultural products and lumber.

Pong!

Do you remember Pong? Based on ping pong, it was one of the first video games that appeared in arcades, bars, airports and many other places back in 1972. It was a huge success for Atari and has been credited with starting the video game revolution. 

I wondered if I could write some code to play this game in a web browser. First though, I asked ChatGPT about it. About 15 seconds later, the AI chatbot replied “Here’s a simple implementation of the classic game Pong” and JavaScript code started scrolling down the screen. This was pretty impressive.

I had seen reports that ChatGPT and other Large Language Models (LLM) could write code. People were predicting that AI would take over a lot of software development and that programmers would be replaced. I had tried a few coding examples myself in the past, with mixed success. I reserved judgment and remained skeptical.

Then a few months ago, Google revealed that about 25% of their code was being created by AI. This was not a rumour or some offhand comment from a Google engineer. It had been boldly stated by Sundar Pichai, the CEO of Google. This claim could not be dispelled so easily. 

So should programmers be fearful of losing their jobs in the new AI world? 

No. 

There’s still some hype in these headlines. There is even hype in my own simple Pong! headline, in that although the dramatic result is true, it is not the whole story.

Yes, ChatGPT produced some running code, but there were a number of things that didn’t work that well, to the extent that nobody would really spend much time playing it. One major problem was a delay in moving the player’s paddle which was annoying and made it hard to hit the ball. Another problem was that the ball would often fall into a repetitive trajectory so that you didn’t even have to move your paddle to keep hitting it.

I explained these problems to ChatGPT, and it replied with some changes for the code that eventually addressed all the problems I found. The end result was a real playable game. 

This highlights the fact that AI is not an independent, automatic force that is in competition with humans and threatens our livelihood and existence. Rather AI is a tool, in fact a collaborator, that allows humans to work more productively and do things that they could not easily do before.

Here is a transcript of my conversation with ChatGPT. You don’t need to understand the code to follow the communication between human and AI, a collaboration that produced the real solution.

If you’re not convinced and are still worried that AI is a threat to humans (here comes HAL), do something to combat climate change. The unrelenting pace of global warming is a far, far greater threat to human existence than is AI.

But enough talk. Get on with the game!

To play Pong, simply DOWNLOAD this file. If it doesn’t automatically open in your browser, double click the file Pong.html in your download folder to open it in your browser. Use the up and down arrow keys to move your paddle. If you don’t hit the ball before it hits the wall, the opposition will score a point.


It’s still a great game, even after all these years.

Good luck!

Computer Memoirs

“Surviving in the Hi-Tech World” follows the many ups and downs of my years as a software developer in the high-tech industry. It provides a window into what it is like to work in the computer field.

I worked for many different organizations, from academia and large companies to medium sized companies and startups. The stories weave my work experience with explanations of the technology of the period. In the process, it is an account of the history of computing, following the revolutionary changes in computer hardware and software from large mainframes to personal microcomputers and the evolution of early networks into the global Internet.

While the book includes technology details down to diagrams and code snippets, there are plenty of human interest stories that will engage non-technical readers.

In university, I became interested in the possibilities of using computers to model and understand human thinking. I completed a Master’s degree in Artificial Intelligence in Computer Science but my interest in doing academic research shifted to an interest in building real world systems. 

My first computer job was with a company that had built one of the first general purpose commercial computers (Univac). I switched jobs for many different reasons – sometimes because of interest and at other times because of necessity. The accounts of how I secured new positions may provide some guidelines for people who are trying to manage a career in the rapidly changing world of technology.

Each chapter in the book covers the different jobs and places that I worked. My journey took me from Montreal to London, Glasgow, Wisconsin, Vancouver and Toronto. Each has its own story and series of adventures. There are accounts of some people who became millionaires and some who went to jail.

This is a free book available in several ebook readers.
Read “Surviving in the Hi-Tech World”