Meeting room designs for both in-person and remote participants
Now that small hybrid meetings are commonplace, what meeting room designs work for a mixture of in-person and remote participants?
Read the rest of this entry »
Now that small hybrid meetings are commonplace, what meeting room designs work for a mixture of in-person and remote participants?
Read the rest of this entry »
I am resigned to the fact that OpenAI‘s Large Language Model ChatGPT has scraped every blog post I’ve written here (over 750 posts in the last 13 years—around half a million words) so it can parrot my thoughts about meeting design, facilitation, and other topics. But I felt surprised, dismayed, and angry to discover that this $10 billion company had misappropriated my copyright, by digesting my copyrighted book Conferences That Work: Creating Events That People Love without any notification, discussion, or thought of compensation.
ChatGPT can be a useful tool. But does its utility justify OpenAI blatantly misappropriating copyright materials for its benefit?
I don’t think so.
We have no idea how many copyrighted works besides my book have been incorporated into ChatGPT. OpenAI has not released any information about the datasets it has used. However, attorneys Shawn Helms and Jason Krieser who specialize in information technology law, write that “The vast majority of the text used to train ChatGPT was certainly subject to copyright protection.” Jenna Burrell, Director of Research for Data & Society, adds:
“The bigger concern is how ChatGPT concentrates wealth for its owners off of copyrighted work. It’s not clear if the current state of copyright law is up to the challenge of tools like it, which treat the internet as a free source of training data. Among other challenges, ChatGPT is fundamentally opaque. It is essentially impossible to track down whose copyrighted material is being drawn from in the prose it produces, suggesting every result may comprise multiple violations.”
—Jenna Burrell, ChatGPT and Copyright: The Ultimate Appropriation
I’m not alone in my concerns. Sarah Silverman and some best-selling novelists with deeper pockets than me have sued OpenAI for “ingesting their books”.
Last week, the FTC opened an investigation into OpenAI, over whether ChatGPT has harmed consumers through its collection of data and its publication of false information on individuals. Though it seems that the investigation focuses on harm to consumers rather than the wholesale misappropriation of copyrighted information, I’m glad that the U.S. government is at least aware of ChatGPT’s impact on society in general.
This brings us to my stake in OpenAI’s land grab. You may be wondering how I know that ChatGPT has ingested a copy of my first book (and, for all I know, my other books as well). I’m not going to provide specific evidence here, though it’s along the lines of the AP News story linked above, and I’m confident that my evidence is persuasive. What I will provide, however, is already in the public domain, via a comment I made to the New York Times story about the FTC investigation into OpenAI [guest link].
In my comment, I shared how OpenAI misappropriated my copyright, provoking many comments and questions to which I responded.
Because the comment thread illuminates and expands on my thoughts, I have reproduced it in full below with my comments in red. I’ve also rearranged the comments so they are in thread order.
To see the thread on the New York Times website:
AJS commented July 13
USA
The content of at least one of my books on meeting design, copyright registered in 2010 with the United States Copyright Office, has been added to ChatGPT’s database without my permission. It was probably scraped from one of the illegal pirate internet libraries of scanned books.
Though I’m weakly flattered that ChatGPT has also incorporated every single post I’ve written on my meeting design blog (over 750 posts in the last 13 years—around half a million words), OpenAI’s flagrant misappropriation of copyrighted works from pirate databases for their own financial gain is beyond the pale.
191 Recommend 16 REPLIES
Robert commented July 13
St Paul
@AJS That’s an interesting argument, but how is ChatGPT’s use of that information substantively different than what data aggregators, including behemoths like Google, have been doing for years?
ChatGPT is just a shell overlayed onto a data set. It processes searches and responses in a natural language format, but that’s more of a superficial than substantive difference.
Are you opposed to all services that have scraped, categorized, and made your writings available, or is there something different about ChatGPT that you’re opposed to?
10 Recommend
AJS commented July 13
USA
@Robert, unlike my blog posts which are freely available for anyone with an internet connection to read, I have never made my copyrighted book available for free public reading on the internet. People have to pay to buy a legal copy.
Do you really think it’s perfectly OK for ChatGPT to illegally add a pirated scanned copy of my book to their database?
42 Recommend
SteveRR commented July 13
CA
@AJS
Copyright refers to “copying” – so the first question is “did ChatGPT copy your work?”
It is more than likely that it did copy your work.
Second, Is ChatGPT Output a Derivative Work?
Most would probably argue that it is not a derivative work
Lastly – the infamous fair use:
If ChatGPT copied your work and such copying was not for a commercial purpose and had no economic impact on the copyright owner then it is probably fair use.
Your lawyers may disagree and that is what courts are for.
3 Recommend
Austin commented July 13
Austin TX
@SteveRR Fair use is specifically for “purposes such as criticism, comment, news reporting, teaching, scholarship, or research”. ChatGPT does neither. However, if it only uses snippets of sentences it would be ok. If it uses entire sentences or more, it could be a violation of copyright. BTW, registration is not necessary under US copyright. Copyright is automatic until the author releases it or waives it.
4 Recommended
SteveRR commented July 13
CA
@Austin
Not even the vaguest of clues where you get your “snippets of sentences” precedent.
Maybe look at fair use on youtube by way of example.
1 Recommend
AJS commented July 13
USA
@SteveRR,
First, OpenAI is not creating LLMs that slurp up everything they can get their CPUs on for the good of mankind. Rather, they are hoping to make a bazillion bucks ASAP. So I think you can make a good case that their use of my copyrighted book is for “a commercial purpose”.
Second, if anyone can get their questions they have about meeting design answered by ChatGPT—which is coughing up a version of everything in my copyrighted books on the topic—why would anyone buy a copy of my books? Under those circumstances, I think you can conclude that OpenAI’s appropriation of the contents of my copyrighted book has an “economic impact” on me.
I am not a lawyer. And I am not going to spend the rest of my life suing the giant corporation that is OpenAI—I have better things to do. But it’s pretty clear that OpenAI’s plundering of copyrighted works for their own gain “because they can” is reprehensible.
1 Recommend
Jacob commented July 13
Henderson
@AJS how do you know it was added to the system, from one of those libraries? Because if your book was widely published, so much so, that it ended up in what you call an online pirate library, is it just as likely that they used book summary sites and online posts describing the contents of your book and not the pirate library, you suspect they used?
1 Recommend
AJS commented July 13
USA
@Jacob, good question. I tested ChatGPT by asking it to summarize the most boring chapter in the book—one which has never been reviewed or mentioned. Search engines do not find any reference to the chapter; it has not been mentioned or extracted in any online review or post.
ChatGPT gave such an accurate summary of the chapter, it’s clear that the platform database includes it in its entirety.
I’ll probably never know how OpenAI got its hands on my book’s contents unless someone with deep pockets sues OpenAI and uses discovery to find out what is included in ChatGPT’s database and where they scraped it from.
5 Recommend
Jlaw commented July 13
California
@AJS on the one hand I see your point, on the other hand I can’t help wonder who really cares about a self published book but the author? I mean, no disrespect, but unless something is being said that isn’t true, I don’t see how an old book is worth depriving humanity from the latest and greatest in technology. This genie broke the bottle.
Recommend
AJS commented July 13
USA
@Jlaw, I suspect the 3,000+ people who have purchased my self-published book cared. Are you seriously saying that a self-published book has no value except to its author?
Recommend
John G commented July 13
Boston
@AJS i agree with you. It seems like a lot of people try to thread the needle for ChatGPT. However, if I upload something copyrighted to YouTube, I get a DMCA take down. That’s because YouTube and I would be making money off of the copyrighted content. The fact that the copyrighted content is obscured the way it is in ChatGPT should make no difference. ChatGPT makes no effort to even reference or cite the source material.
It could even be argued that chatGPT is a derivative work when it provides snippets “in the style of” an author.
If I make a performance from a book, I have to acquire rights to do so. ChatGPT is a performance assembled from “samples” of other peoples work.
chatGPT is blatant intellectual property theft and should be shuttered with cease and desist orders until this is resolved. There are plenty of LLM efforts that have a much cleaner pedigree than chatGPT so we would not lose much in terms of technological advancement.
2 Recommended
Observer commented July 13
NYC
@AJS This is a fascinating case, but you are blurring lines between three concepts: (1) stealing one copy of your book, (2) copyright, and (3) attribution.
On piracy: OpenAI clearly owes you the $25 (or whatever it costs) for access to your book. But that doesn’t really seem to be what is bothering you.
On copyright: OpenAI could be violating your copyright whether or not they bought your book. If they bought it legally and then reprinted exact passages, that would be a copyright violation. But the way OpenAI answers questions is arguably no different than a person who has learned the material. If I buy one of your books and answer questions someone asks me about it, that doesn’t necessarily make me a copyright violator.
It is a brand new technology that poses problems that aren’t addressed by copyright law. And, personally, I sincerely hope they are *not* found to be violating copyright law because the potential value of their service is so great. Transformational, really, in areas like medicine.
On credit: OpenAI should arguably still credit you as the source for their information. And I am certain they are working on this.
But so far, it seems like you are out $25. A bit piratical, but not a flagrant misappropriation.
2 Recommend
AJS commented July 13
USA
@Observer, but OpenAI _didn’t_ buy a copy of my book and then incorporate it into their database. And they have no intention of doing so.
Your argument is equivalent to saying someone can steal thousands of books from a bookstore, and if they get caught they can just pay for the books and everything is fine. I’m not sure our society would work so well if that was how copyright worked.
1 Recommend
John G commented July 13
Boston
@Observer if chatGPT is like a person, then you could say it is answering questions like a human. If it is like a program, then it is answering from the raw data.
It is most decidedly not like a person.
The “person” here is openai the corporation, which has used a vast array of copyrighted work to create a commercial product which makes money off of that copyrighted work. This would be no different than a company of hundreds of employees buying one copy of a book, copying it to all employees to enable them to answer questions, which violates the author’s rights.
Recommend
JN commented July 13
NY
@AJS
For the sake of argument, are you ok if OpenAI actually paid for a copy of your book before using it as training data for ChatGPT in the pursuit of knowledge?
Recommend
AJS commented July 14
USA
@JN,
As pointed out in earlier comments, OpenAI purchasing one copy of my book…
1) …didn’t and isn’t going to happen, and
2)…doesn’t give OpenAI the right to use it in ways that violate my copyright (see the argument about fair use).
Just as movie studios don’t get the right to make a movie of a book if they buy a copy—they typically pay a few percent of production costs to the copyright owner.
Just as libraries don’t have the right to buy and scan one physical book and lend it to as many patrons as they like. Libraries also negotiate payments that are far more than the retail cost of an ebook for the right to lend it to multiple patrons.
OpenAI has ignored these and other existing compensation models for copyright holders and simply taken everything they wanted for their database without discussion or a shred of conscience.
Recommend
OpenAI has misappropriated my copyright. I’m not happy about this, and pessimistic that this huge tech-bro-driven corporation will be brought to heel for its immoral behavior. Some authors and artists have responded by deciding to remove their content from the internet. I think this is the wrong approach. I want large corporations like OpenAI to stop misappropriating copyrighted work. OpenAI has several ethical options. The company could:
Any of these options would be a positive step, showing respect for the creators of copyrighted material, rather than misappropriating their work.
Sorry folks, but ChatGPT is just a tool, like a hammer, pen, spell checker, or Grammarly. Like any tool, ChatGPT can be useful—and it can also be dangerous when used incorrectly.
ChatGPT is a tool called a large language model (LLM). However, marketers love to call ChatGPT and other LLMs artificial intelligence (AI) because this framing ties into our culture’s fascination with understanding who we are, how we’re able to do what we do, and whether we are unique in our abilities or not. This fascination causes us to give human names to familiar objects, like cars, and to anthropomorphize our pets and tools. Harnessing fascination is a good way to sell us stuff.
I’ve programmed computers for over half a century and taught college computer science from 1983 – 93. Computer researchers began to use the term artificial intelligence in the 1940s and 50s.
In 1993, JET Thomas and I conducted a seminar at Marlboro College on AI. At that time, a second AI winter held sway. Rule and frame-based systems predominated. Researchers had not implemented key components of effective neural networks, our current core AI technology. The best chess-playing programs could beat most players, but Grandmaster Gary Kasparov wouldn’t lose a chess match to a machine until 1997. During the seminar, teachers and students alike shared a fascination with the concept of AI. However, the technology of the time generated output that was completely determined by the rules built into its programs.
However, unlike the software available during our 1993 seminar, humans can’t determine how today’s LLMs come up with their responses. And these sophisticated neural networks, often called deep learning, are everywhere. We use them for speech and image recognition, and natural language processing. ChatGPT has been used to “write and debug computer programs, compose music, teleplays, fairy tales and student essays, answer test questions (sometimes, depending on the test, at a level above the average human test-taker), generate business ideas, write poetry and song lyrics, translate and summarize text, emulate a Linux system, simulate entire chat rooms, play games like tic-tac-toe, or simulate an ATM.”
Just because ChatGPT can be asked to do these things doesn’t guarantee that it creates reliable answers. The software’s creator, OpenAI, acknowledges that ChatGPT “sometimes writes plausible-sounding but incorrect or nonsensical answers”.
Here’s a simple example of the limitations and unreliability of ChatGPT.
I asked ChatGPT to rewrite a passive voice sentence in an active voice.
Me: rewrite “Try not to get stuck.” as an active sentence.
ChatGPT: ”Make an effort to avoid getting stuck.”
Me: That’s still a passive sentence!
ChatGPT: Apologies for that oversight. Here’s an active sentence version:
“Strive to avoid getting stuck.”
Me: Still passive!
ChatGPT: I apologize for the continued oversight. Here’s an active sentence version:
“Take proactive steps to avoid getting stuck.”
Me: “getting stuck” is passive, you’ve used it each time. rewrite it.
ChatGPT: Apologies once again for the oversight. Here’s an active sentence with a revised phrase:
“Make an effort to prevent becoming trapped.”
Me: “becoming trapped” is passive too. You’ve failed.
ChatGPT: Apologies for the repeated oversight. Here’s an active sentence with an active phrase:
“Exert effort to evade getting trapped.”
Me: Grammar is not your strong point.
ChatGPT: I apologize for the errors in my previous responses. I appreciate your patience, and I’ll make sure to provide a correct and active sentence for you. Here’s an active version of the sentence:
“Strive to avoid getting stuck.”
<Sigh>.
This and numerous other examples of the confident fabrications of ChatGPT have led many to characterize it—fairly in my view—as “an automated mansplaining machine“, “autocomplete on steroids“, and a “bias optimizer“. As the third reference points out, “ChatGPT cannot recontextualize or independently seek out new information that contradicts [its] built-in assumptions.”
In the above example, it would have been refreshing if ChatGPT said at some point, “Sorry, I don’t know how to do that.” Instead, it repeatedly declared it had the answer. Hence the danger of using this tool. You have no guarantee anything ChatGPT avows is actually true! How can we use something we can’t completely trust?
The answer is: Carefully!
In 2019, I wrote about my concerns about the impact of machine learning on the future of work. Recently, people have written thousands of articles about how LLMs like ChatGPT jeopardize the future work prospects of numerous professions.
Some bosses will undoubtedly believe that they can replace some employees with fewer people writing well-prompted responses from ChatGPT. Such beliefs are dangerously naive. Here are three examples of the problems that can arise:
All new technology transforms job scope over time. But only some, like the automobile, eliminate industries. ChatGPT, by making some forms of work more efficient may allow employees to be more productive, meaning a static industry may be able to employ fewer workers. But I don’t see the wholesale future elimination of lawyers, writers, software makers, and other professions that many predict.
My advice is to think of ChatGPT as just a tool. Knowing when and how to use a specific tool is important. For example, as I write this post I’m using Grammarly to check my spelling and grammar. It’s a useful tool that catches most of my errors on the fly and occasionally improves how I express myself. However, it often makes suggestions that are simply incorrect and need to be suppressed. If I relied on Grammarly 100% to proofread my work, errors would slip through. (Regardless, I’m not claiming I’m a perfect editor of my own work!)
Similarly, I find ChatGPT useful for suggesting possible blog post titles, summarizing articles, and brainstorming ways to express ideas in print. However, most of the LLM’s suggestions are not helpful to me; I always need to review them to determine if there’s anything worth using.
In conclusion, treat ChatGPT as a useful but fallible tool, rather than an oracle. And don’t worry too much about its impact on your future work prospects!
For the last 16 years I’ve posted one or more blog posts each week. Every post includes at least one image — over 1,400 blog post illustrations to date. Some of them are my own photographs, screenshots, or public-domain images. But the majority I create myself. I’ll never be a great graphic artist, but I enjoy visualizing and creating these visual reinforcements to my posts and am always looking for new tools that a novice like me can use successfully.
In 2019, I wrote about two free and easy ways to create graphics: Canva and Keynote. Well, I’ve added three more tools to my artist’s palette. They’re not free, but they’re inexpensive and I think they’re well worth the cost. You can, of course, use them for presentation illustrations too. So without further ado, here are three great tools for blog post illustrations.
I mentioned this $39.99/year tool at the end of the above 2019 post, but I’ve used it so much since then that I’m promoting it to “get-it” status. Noun Project describes itself as “Icons for Everything: Over 2 million curated icons, created by a global community”. You get unlimited royalty-free large SVG & PNG icons arranged in a searchable catalog. You can set the color of any downloaded icon. Noun Project is especially useful when trying to convey abstract concepts.
Here are a few of the ways I’ve used it:
A Noun Project subscription also includes a small library of “stock” photos that I’ve occasionally used.
Here’s a mind-blowing tool. Midjourney is an AI image creator that I am increasingly using for illustrations for my blog posts.
For example, for last week’s post on my top 10 digital tools for learning in 2022, Midjourney created this image as one of four generated with the simple prompt “top 2022 tools photorealistic”.
Typically, I’ll use Midjourney images to build a composite illustration. Here’s an example from a recent post: What meeting planners who support women’s rights can do.
And here’s an image generated from the prompt “50 people meeting” with a few copies of the CDC’s digital representation of SARS-CoV-2 added at various sizes:
I should emphasize that I spent very little time creating these images. Others, with some work, have produced beautiful Midjourney images like these:
Midjourney is still in beta. (And may be for some time.) You need a (free) Discord account to use it.
Currently, you can sign up for a free trial of Midjourney at discord.gg/midjourney. Free users are restricted to a limited number of image generations. I subscribed to the Basic plan for $10/month which allows me to generate about 200 images per month, far more than I need.
I’ve only scratched the surface here. AI image generators like Midjourney are game-changers for the world of illustration. (Yes, there are others, like the free, ad-supported, Craiyon, but Midjourney is my favorite to date.) I strongly recommend you check out Midjourney.
Finally, there’s SketchWow. This is a great tool, available on Mac or PC, for adding a cartoon-casual, hand-drawn look to your blog post and presentation illustrations. Think of it as a drawing program for amateur cartoonists.
A glance at some of the SketchWow starter templates will give you a sense of this tool…
In the past, I’ve used OmniGraffle to create diagram-style illustrations. SketchWow has the same capabilities but produces more attractive results. You can include animated connectors and icons. SketchWow’s onboarding is straightforward, the user interface is intuitive, and the online help is clear. The core menu elements are easily accessible and what you’d expect.
Here’s an example of how I used SketchWow for a blog post illustration. I combined a photo image from Noun Project with speech bubbles from Sketchwow. This was all done inside SketchWow. The sizing and positioning of the speech bubbles were quick and intuitive.
Pricing for SketchWow is a little, well, sketchy. If you go to Sketchwow’s website and click on Pricing, it looks as though it’s a subscription product, with the basic plan costing $19/month. It’s not worth quite that much money to me. However, SketchWow is currently also being sold as a one-time purchase, lifetime-updates product for $49. At that price, I recommend it!
If so, please share them in the comments below!
I just built a Corsi-Rosenthal Box. You might be thinking “What?” Well, it’s a simple and inexpensive DIY air filtering device that helps remove airborne viruses, wildfire pollution, pollen, dust, etc. from indoor air. Of particular note: the filters used are good enough to remove COVID-19 aerosols from contaminated air. Also, it’s incredibly easy to build and inexpensive. My Corsi-Rosenthal Box took less than an hour to make using the readily available supplies shown above. And it cost just $94 plus a dollar or two for duct tape.
That compares favorably with the $230 sleek Coway Air Purifier, shown below, that I purchased at the start of the COVID-19 pandemic. Especially since the latter is rated at ~250 cubic feet per minute (CFM) while mine provides ~350 CFM.
My air filter is 40% of the price of the Coway yet provides 40% more ventilation!
To be fair, mine is larger — and uglier. Here it is!
Even though I’d never made one before the air cleaner took less than an hour to put together. If I did it again, I think I could build one in less than 30 minutes.
All the materials I used are shown above. Here’s the list:
The only tools I needed were a Swiss army knife, scissors, a pencil, and a loop of string. (Oh, and a thumbtack.)
Because there are already good resources available for choosing components and building a Corsi-Rosenthal Box, I’m not going to replicate them here. Instead, here’s what I found most helpful:
These resources cover everything you need to know to build inexpensive and effective air cleaners, plus a little interesting history of how they came to be.
While building my box I learned some little details that aren’t covered in the core resources above. None of them are vital, but they might help you. Here they are:
How should the four filters be duct-taped together? See the picture above, which shows the seam arrangement I used to create a square shape. I found that 2″ duct tape worked well for the entire project.
I purchased my fan and filters online, and both got shipped in boxes that are the perfect size to provide the cardboard you need. I used the Lasco fan box for the box base (see below), as well as four pieces needed to seal the corners of the fan mounting and the fan shroud (see next two sections). Very little cardboard was left!
Note that I sealed the bottom of the box along the filter edges and added four additional short strips of duct tape at each corner to reinforce the construction.
Here’s how I marked up the other side of the Lasco fan box to create four corner arcs that sealed the fan mounting and the fan shroud (see next section).
I placed the fan in the center of the cardboard and drew around its edge, creating the outside pencil line as shown below.
After removing the fan, I used a tape measure to find the center of the cardboard and inserted a thumbtack. Then I made a loop of string to draw a circle to cut out for the air exhaust portion of the fan shroud. (Look at the earlier photo of my finished unit to see what the fan shroud looks like.) The right length for the loop will depend on the fan you use. Here are the optimum fan shroud openings (with the 3M Filtrete 1900 filters I used) for two common fans:
So for my Lasco fan, I used a 15″ loop of string to draw a central circle with a 7.5″ radius.
After marking the cardboard I cut the four fan seal corner arcs from the cardboard corners with my Swiss Army knife and duct-taped them in position as shown below.
I then cut out the fan shroud.
All that remains at this point is to place the fan on the top of the box and seal it to the filter edges and the corner cardboard arcs with duct tape. Finally, tape the edges of the fan shroud to the fan.
You’re done! Here, again, is the finished unit.
This Corsi-Rosenthal Box is quiet, even on maximum fan speed, and noticeably more powerful than my commercial Coway unit. I live in a very airtight home — my CO₂ meter shows significantly higher readings when just the two of us are there. So I am happy to have this second unit available when folks visit. Building it was fun and easy. Recommended!
TLDR: Useful if Tesla Powerwall frequency shifting during outages is affecting appliances like clocks, furnaces, uninterruptible power sources (UPS), etc. Want to skip right to fixing the Tesla Powerwall frequency problem? Click here.
In February 2018, we installed a Tesla Powerwall 2.0 on our Vermont home. We get around thirty outages a year, and for the last 7 years this device has provided us with a reliable automatic backup electricity source capable of running our home through outages of up to two days. (Read more about my experience with our Tesla Powerwall here.)
Whenever there was a lengthy outage, I noticed that my old-fashioned digital clocks would run a little fast. I’d reset them to the correct time and didn’t think much about it.
Until one day…
Earlier this year, I reluctantly dismantled our 38-year-old solar hot water and space heating system and replaced it with a gas boiler. (One of the system’s large, expensive solar storage tanks had sprung a leak, and I would have had to replace all three tanks. Our solar collectors were still working flawlessly, but I worried that they might not last much longer.)
The gas boiler, a high-efficiency Alpine condensing boiler, was installed to heat a new stainless steel domestic hot water tank and the two existing radiant floor heating systems. After dealing with the inevitable teething troubles, the system was working well.
Until we had a power outage while the boiler was running.
Passing the small utility room that contains the heating system, I noticed a red glow that was definitely not normal. Going in, I saw that the boiler’s touchscreen display had turned red. The boiler had shut down with a “hard lockout”. Looking up the displayed error message “Fault 23” told me that the boiler was unhappy with the Tesla Powerwall’s power.
This was not OK. First, the boiler would not operate during a power outage. Furthermore, it would not turn on automatically once utility power returned. That’s because you have to manually reset the hard lockout using the boiler’s touch screen.
So if we left our home for a few days and a power outage occurred during that time, the boiler would not operate until someone entered our home and reset it. Having our plumbing freeze and plants die while we were away was not acceptable.
It wasn’t hard to figure out what was happening, once I remembered the previously ignored clue that some of our clocks ran fast when using Powerwall power. These clocks are the old-fashioned kind that keep time based on the national electric utility frequency of 60 hertz (Hz). Clearly, the Powerwall must be providing backup power at a higher frequency.
To my surprise, a quick Google search told me that Powerwalls supply power at 66 Hz when they are at full or close to full charge! My furnace was shutting down because, unlike the rest of my appliances, it would not operate correctly at 66 Hz. But why would Powerwalls do this?
Well, it turns out that many Powerwalls are used as storage for photovoltaic (PV) solar panels. PV systems also use an inverter, like the one in a Powerwall, to generate household power. And when the house’s electrical needs are being met with the Powerwall charged to or near full, there’s nowhere for additional solar-generated electricity to go. So the Powerwall is designed to switch to 66 Hz under these conditions. PV inverters, like my furnace, see the frequency out of the normal spec and shut down. The Powerwall supplies the home until it has spare capacity to be recharged by the solar panels, and then drops its frequency down to 60 Hz. Until then, the solar inverter (and my furnace) will shut down.
Ok, so I understand the problem and the reason Powerwalls are designed this way. But I don’t have PV panels, and I want my furnace to work when there’s a power outage! What could I do?
Luckily, as you might expect, I wasn’t the first customer to have this problem. More Googling indicated that I could call Tesla and ask them to remotely update my Powerwall to reduce the frequency of power it provided under high charge conditions.
So I did. After a long hold time for Tesla Powerwall Support [(888) 765-2489], I spoke with a friendly technician, Manny. He confirmed that Tesla would make this change and placed an order for my system. Manny told me the change usually took 3 – 5 business days, and he would get back to me when they did it.
I waited. After nine days, I called back to get an update, and Andrea told me the queue was currently running 10 – 15 business days. So I waited some more.
Sixteen days after I’d spoken with Manny, he emailed me that Tesla had made the change. Great! Now, I wanted to test to see if the fix worked.
I didn’t want to wait until a power outage occurred while my furnace was running. So I decided to manually switch our home to Powerwall power.
I hadn’t done this before, so I investigated my Powerwall installation. It’s mounted on an external wall, so it’s easy to see the components. Please note that there are several ways to install Powerwalls — don’t assume that your configuration will be the same as mine. Here’s a photo, with the components labeled, of my setup.
Grid power flows through my utility meter through the gateway to the Powerwall disconnect, which is hooked up to both the Powerwall and my main home breaker panel.
For my setup, to switch our home to Powerwall power manually you simply have to open the gateway box and turn off the grid disconnect switch.
After flipping the grid disconnect switch, I went inside and turned up a thermostat so our boiler would fire up. Success! The Alpine now worked happily on Powerwall backup power!
I don’t own a multimeter that includes frequency measurement, but I found another way to discover the frequency that my Powerwall now generates. By logging in via your gateway’s Wi-Fi network, it’s possible to view the operating frequency of your Powerwall. These instructions provide a guide. I discovered that my Powerwall’s output is now between 62.1 and 62.3 Hz. Apparently, that’s close enough to 60 Hz to keep the boiler running.
Although I solved my boiler problem, that doesn’t mean other appliances or devices are immune from Tesla’s frequency-switching technology. If that turns out to be the case for you, there is another option that should work, though you’d have to pay for it.
The trick is to use an online aka double-conversion uninterruptible power supply (UPS) to power the troublesome device. (Offline/Standby, Line-Interactive, and Automatic Voltage Regulation types of UPS don’t change the frequency of the power supplied.) An online UPS charges a battery that runs an inverter providing 120 volts, 60 Hz power independent of incoming power quality. When grid power fails, this type of UPS has no transfer time. Plug the problematic device into an online UPS that has enough volt-amp (VA) capacity and you’re all set. Note that the backup time such units provide is irrelevant since they will still be receiving power from the Powerwall.
The only drawback to this solution is the expense. An online UPS costs more than the other types. The least expensive unit I could find via a quick search, the Maruson 1000VA Online Double-Conversion UPS, costs almost $500.
Once again, I’m very happy with my Tesla Powerwall. It would be nice if an installer or owner could make this frequency change, rather than waiting for two weeks for Tesla to do it. But at least there was a fix that only cost some time for research and a couple of phone calls, and my boiler power problem was resolved.
I hope this article will help anyone else who runs into the same problem. Please share your experiences and suggestions in the comments below.
I’m a big proponent of fishbowls as a tool to manage wide-ranging group discussions. (To learn in detail about the use and implementation of fishbowls and fishbowl sandwiches, see Chapters 29 and 30 of my book Event Crowdsourcing.) So when I heard about a free tool for online fishbowls — Stooa — I thought I’d take a look. Here’s my Stooa review.
It’s easy to start working with Stooa. Registering a (free) account requires the usual information: name, email, and password. You can also add your Twitter and/or LinkedIn profiles if desired.
Once you’ve registered your account, you’re ready to create a new fishbowl.
As you can see, you can specify a discussion topic, add a description, and schedule the fishbowl start and duration (up to four hours; though that would be cruel and unusual punishment). You can also choose a language to use. Currently, the choices are English, Spanish, French, and Catalan. On clicking Create fishbowl you’ll see a summary of your new fishbowl, together with a link to distribute to others so they can join it. You’ll also receive an email with the same information — a nice touch.
When you click on Go to the fishbowl, Stooa will ask for permission to use your camera(s) and microphone(s). (Once you’ve joined a fishbowl, you can choose which ones to use.) Enter how you’d like to display your name, and you’ll see this screen:
When you’re ready to begin, click Start the fishbowl. At this point, the camera and microphone will be active just for you. Share a short introduction with the waiting attendees. When done, you’ll appear in one of the five fishbowl “seats”. Click Allow attendees to join the conversation to begin a discussion.
At the top of the screen, you’ll see the remaining time for the fishbowl, a button to end it, and the number of attendees present. Clicking on the latter displays a list of people currently in the seats, followed by the remaining attendees. The list includes links to the Twitter and LinkedIn profiles of each attendee if they entered them.
At this point, attendees can enter/leave one of the fishbowl seats by clicking on the Join/Leave the conversation button at the bottom of the screen. The other buttons allow participants to choose and control their camera and microphone.
Five participants is a good maximum for a controlled and useful discussion. Stooa smoothly implements the entry and departure of fishbowl participants.
When your discussion is over, use the End fishbowl button to close the session.
Here are my initial impressions from a brief look. First, I want to acknowledge Stooa’s creator, Runroom, for developing this tool and making it Open Source: software with source code that anyone can inspect, modify and enhance. Hosting the software so that anyone can use it is another Runroom gift. They explain why they did so here. Thank you Runroom!
Stooa was easy to register and use on Chrome or Safari. First-time users should have little difficulty, as the entire onboarding process is designed very well. I haven’t used the tool with a large number of attendees, so I can’t say how it holds up under load. Given that the number of folks simultaneously on video chat is limited to five, I expect it will work fine.
Stooa succeeds admirably in its purpose as a single process tool that facilitates effective group discussion.
Currently, you can’t remove a fishbowl participant. This could be a problem if you used Stooa for a public fishbowl discussion, publicized via a link on social media.
In addition, with all seats filled, there’s no way for waiting attendees to indicate that they’d like to join the discussion, so a fishbowl host doesn’t know how many others are waiting to speak. To deal with this, attendees could use a backchannel tool like Slack to message the host that they’d like to join in. Alternatively, adding a hand raise option to the attendee list would help to solve this problem. And incorporating a simple text chat for all attendees into Stooa would provide even greater flexibility.
Stooa is not the only tool for running online fishbowls. In July 2020, I shared how to use Zoom to run fishbowls online. Zoom is, of course, a fee-based platform, but many organizations own a license and Zoom does many other things as well. In this situation, Zoom includes attendee text chat and hand raising. And its breakout rooms allow you to create, inside a single tool, the fishbowl sandwiches I use to facilitate group problem-solving.
In an ideal world, the tools we use would include only the features we need. We don’t live in such a world, and Stooa is a well-crafted platform that allows groups to meet and discuss online. Whether it includes everything you need to make such discussions effective and fruitful is ultimately up to you to decide.
I hope you’ve enjoyed this Stooa review and found it useful. Here are some additional resources for exploring Stooa. Feel free to add your experiences and thoughts in the comments below!
The COVID-19 pandemic has devastated the in-person meeting industry. Though it took too long to recognize that COVID-19 spreads via air transmission, we finally have effective procedures (vaccine mandates, masking, air quality standards, and social distancing) to reduce infection risk at in-person meetings. Now, meeting planners can add an affordable air quality tool to their site visits.
Look around the room at an in-person event and you’ll see if masking and social distancing are taking place. We can implement vaccination mandates using third-party vendors such as sharemy.health, CLEAR Health Pass, Safe Expo, and others. But how can we determine the air quality at a prospective venue?
Currently, we don’t know how to detect airborne COVID-19 viruses. (This is likely to be true for a long time. We still have no test for airborne tuberculosis bacterium (TB) transmission two centuries after identifying TB as a distinct disease.)
Luckily, under the conditions I’ll outline below, we can obtain useful information about a venue’s air quality by using a device that measures a proxy for air pollution: carbon dioxide (CO₂).
People breathe in air, typically containing about 0.04% CO₂. They breathe out a mixture of gases containing about 4 – 5 % CO₂. People with COVID-19 co-exhale respiratory aerosols containing the SARS-CoV-2 virus.
If an occupied building space has effective ventilation, the occupants’ excess exhaled CO₂ is quickly diluted with fresh air, and the CO₂ level in the air remains close to normal values. Measuring the level of CO₂ in the air can, therefore, tell us whether effective ventilation is present or not.
Here are the generally accepted standards for CO₂ levels:
Until recently, meters that measure CO₂ levels in the air cost hundreds of dollars. (Some models with especially accurate sensors or the capability to measure other air pollutants still do.) But today we can buy an affordable air quality tool — a hand-held CO₂ meter for under $100. The one I just purchased (illustrated above) cost $80, and there’s a wide variety to choose from (for example, from here or here).
My 3.27″ (diameter) x 1.26″ (depth) meter measures CO₂ levels from 0 – 5,000 ppm. It can run on standby for 18 hours, supports USB charging, and includes a battery level indicator and temperature and humidity readings. While its specifications omit accuracy, inexpensive CO₂ meters are typically reliable within ±100 ppm. This is good enough to provide a decent estimate of the air quality in an enclosed space.
My unit shows a concentration of ~350 ppm CO₂ outside my rural Vermont home, which was built tightly. In my home office, the level increases to about 450 ppm and rises to about 525 ppm if I’m sitting next to the unit for a while. Slightly cracking open a window quickly brings down the reading.
I haven’t had time to explore other buildings yet, but am looking forward to seeing what I find out when I do.
Can measuring CO₂ levels give us a useful indication of indoor air quality?
The answer is a qualified yes. It depends!
First of all, we need to measure CO₂ levels in occupied spaces. A meeting planner doing a site visit should take CO₂ readings in occupied meeting rooms, restaurants, hotel lobbies, etc. Taking measurements in empty spaces will only show high readings if the building ventilation system is grossly inadequate (with CO₂ infiltrating from other areas.) Also bear in mind that increasing the number of occupants in a space increases the likelihood that an infectious person will be present and the number of people possibly infected. Doubling occupancy can thus cause a four-fold increase in risk of transmitting COVID-19.
Second, there are sources of CO₂ that are not related to human exhalation but will increase meter readings. A common source is combustion emissions such as gas stoves, which can significantly increase CO₂ levels. Pets can also increase CO₂ levels, though animals are unlikely to be sources of the COVID-19 virus. Such sources will cause increased levels of CO₂ without increasing the incidence of COVID-19 transmission.
Finally, air treatment options, such as MERV 13 or better filtering, or possibly ultraviolet-C radiation, may reduce the prevalence of active COVID-19 aerosols. When venues employ these mitigation strategies, CO₂ levels will not be decreased. Of course, if a venue has deployed these preventative measures, they will surely inform you about them when asked!
Due to these factors, you shouldn’t rely solely on measurements of CO₂ levels to determine whether a space is ventilated enough to mitigate transmission risk.
However, a simple CO₂ meter like the one I now own can be an effective air quality tool, providing valuable information to anyone who wants to investigate the air quality of occupied spaces at venues, hotels and properties, restaurants, and other meeting locales. I’ll be bringing mine when I travel, and I encourage you to do this as well!
If you’d like to learn more about the relationship between CO₂ levels and COVID-19 exposure risk, here are some useful references:
And here are some less technical media articles on CO₂ meters:
Attention, meeting planners! Safe meeting venue ventilation for COVID-19 is critical. As we start thinking about returning to in-person events, it’s crucial to check that venues are upgrading their HVAC systems to handle potentially virus-infused air.
There has been little public discussion on this important topic. In this post, I’ll explain why questions about venues’ HVAC safety should be at the top of your site visit checklist.
Before we start, I need to make clear I’m not an HVAC engineer. My (perhaps) relevant background is an ancient Ph.D. in high-energy particle physics. I also spent two years spent exploring ventilation systems—specifically air-to-air heat exchangers—when I owned a solar manufacturing company in the 1980s.
Since the pandemic began, the science of COVID-19 transmission has evolved rapidly. Because early theories turned out to be inaccurate, current preventative measures are frequently misdirected. So I’ve included a short history of theories of COVID-19 transmission. These shed light on the reasons we’ve underestimated the importance of ventilation in creating safe environments for indoor events.
Next, I’ve outlined what current research indicates venues and properties should be doing.
Finally, I’ve aired my concerns about how well venues and properties are responding to the safety concerns I’ve introduced.
Early reports on SARS-CoV-2 virus transmission falsely concluded that surface contamination was a significant transmission vector.
“COVID-19 is transmitted via droplets and fomites during close unprotected contact between an infector and infectee. Airborne spread has not been reported for COVID-19 and it is not believed to be a major driver of transmission based on available evidence.” [Emphasis added]
—Report of the WHO-China Joint Mission on Coronavirus Disease 2019 (COVID-19), February 2020
This led to an epidemic of another kind—regularly cleaning and disinfecting surfaces. Meeting industry venues that have remained open during the pandemic adopted cleaning and disinfecting everything in sight as a visible assurance that their venues were safe places to gather.
“By May, [2020] the WHO and health agencies around the world were recommending that people in ordinary community settings — houses, buses, churches, schools and shops — should clean and disinfect surfaces, especially those that are frequently touched. Disinfectant factories worked around the clock to keep up with heavy demand.”
—COVID-19 rarely spreads through surfaces. So why are we still deep cleaning?, Dyani Lewis, Nature, January 2021
However, current research suggests that the risk of infection from touching a heavily contaminated surface is less than 5 in 10,000. This is considerably lower than current estimates for SARS-CoV-2 infection through aerosols.
Despite this information, the current GBAC STAR™ Facility Accreditation Program for Cleaning, Disinfection, and Infectious Disease Prevention Accreditation Handbook concentrates on cleaning and disinfecting surfaces. The handbook barely mentions venue ventilation for COVID-19. The International Association of Venue Managers (IAVM)’s Public Assembly Facilities Recovery Guide (October 2020) has a section on HVAC systems, but still provides much more detail about cleaning and disinfecting.
By the way, the American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE) recommends that cleaning activities be performed after hours, rather than during meetings because “Vacuuming, sweeping, curtain cleaning, brooms, could potentially re-suspend infectious particles.” [ASHRAE Epidemic Commercial Task Force recommendations, updated March 2021, Page 10.]
After scientific consensus quickly moved to droplet transmission as a significant factor, face masks were strongly recommended, and mandated at most in-person meetings. However, there have been numerous reports of lax mask usage during F&B breaks and socials.
Social distancing was also recommended. Why? Because it was thought that the COVID-19 virus was mainly transmitted via large respiratory droplets that fall quickly. This belief is still popular and frequently cited today.
Unfortunately, the latest research now points to aerosol transmission of COVID-19 as a significant vector. Aerosols are small droplets and particles (formed when small droplets dry quickly in the airstream) that can remain suspended for many minutes to hours. They can travel far from the source of air currents. An excellent summary of this research is included in The Lancet‘s April 15, 2021 article: Ten scientific reasons in support of airborne transmission of SARS-CoV-2. Here’s the key introductory paragraph:
If an infectious virus spreads predominantly through large respiratory droplets that fall quickly, the key control measures are reducing direct contact, cleaning surfaces, physical barriers, physical distancing, use of masks within droplet distance, respiratory hygiene, and wearing high-grade protection only for so-called aerosol-generating health-care procedures. Such policies need not distinguish between indoors and outdoors, since a gravity-driven mechanism for transmission would be similar for both settings. But if an infectious virus is mainly airborne, an individual could potentially be infected when they inhale aerosols produced when an infected person exhales, speaks, shouts, sings, sneezes, or coughs. Reducing airborne transmission of virus requires measures to avoid inhalation of infectious aerosols, including ventilation, air filtration, reducing crowding and time spent indoors, use of masks whenever indoors, attention to mask quality and fit, and higher-grade protection for health-care staff and front-line workers. [Emphasis added.]
You can think of COVID-19 aerosols as cigarette smoke, or the aroma from cooking food. Of course, aerosols diffuse over distance, which is why social distancing is still a good idea, and why transmission of COVID-19 outdoors is unlikely unless people are tightly packed together. Incidentally, this means that if you’re eating or drinking at a restaurant or bar and can smell the food of diners at a nearby table or the smells of cooking from the kitchen, you’re not in a safe situation as far as COVID-19 transmission is concerned.
Interim guidance published by the California Department of Public Health points out that standard building environments have not been engineered to control exposures to small aerosols of hazardous viruses, such as COVID-19:
“Our understanding of the role that the built environment plays in the transmission of COVID-19 is evolving; recent literature has clearly demonstrated small aerosols can be carried well beyond the six (6) foot physical radius and remain suspended in room air where they can be inhaled. With the possible exception of hospitals, healthcare facilities, and research facilities that employ exhaust hoods, existing ventilation requirements, such as those established in the California Building Code and Title 24, were not intended to control exposures to small aerosols of hazardous infectious agents such as COVID-19.” [Emphasis added]
—General Considerations extract from the Interim guidance for Ventilation, Filtration, and Air Quality in Indoor Environments, California Department of Public Health, February 21, 2021
The American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE) points out that many existing mechanical air filters will not remove enough levels of airborne COVID-19:
“ASHRAE recommends that mechanical filter efficiency be at least MERV 13 and preferable MERV 14 or better to help mitigate the transmission of infectious aerosols. Many existing HVAC systems were designed and installed to operate using MERV 6 to MERV 8 filters. While MERV 13 and greater filters are better at removing particles in the 0.3 micron to 1 micron diameter size (the size of many virus particles) the higher efficiency does not come without a penalty. Higher efficiency filters may require greater air pressures to drive or force air through the filter. Care must be taken when increasing the filter efficiency in an HVAC system to verify that the capacity of the HVAC system is sufficient to accommodate the better filters without adversely affecting the system’s ability to maintain the owner’s required indoor temperature and humidity conditions and space pressure relationships.” [Emphasis added]
—ASHRAE Epidemic Taskforce Building Readiness (updated March 16, 2021)
The above ASHRAE guidelines explain that you cannot simply swap existing filters with MERV 13 or better filters and pronounce your building “ready” to handle potentially COVID-19 infected people. Venues and properties will typically need to involve “licensed and certified professionals and companies that can perform the analysis, testing, design, construction, control programming, balancing, commissioning, maintenance and operation services required to make the adjustments and achieve the performance included in these recommendations.”
Major heating plant upgrades may be needed to create safe air quality for occupants.
Finally, many properties and venues have been operating in low-occupancy mode for long periods. Reopening such buildings safely, even to pandemic-appropriate occupancy levels, can require several weeks of preparation for the HVAC plant and facility staff. Here is what the Centers for Disease Control and Prevention (CDC) recommends be done before resuming business operations:
—COVID-19 Employer Information for Office Buildings, CDC, updated April 7, 2021
I’m concerned about the lack of visible venue and property efforts to resolve the ventilation safety issues caused by COVID-19.
Over the last couple of months, I’ve reached out to industry contacts and meeting professionals on social media. I’ve asked for examples of venues and properties that have implemented (or are implementing) ventilation upgrades that will satisfy recent interim comprehensive guidelines such as those published by ASHRAE and the California Department of Public Health.
To date, I have heard of only one venue—a California hotel property that installed MERV 13 filters. If your venue has made or is making such upgrades, please let me know, either directly or via comments on this post.
Perhaps many venues are quietly making these changes. I hope that’s the case.
Perhaps some venues are ignoring the problem, hoping that, somehow, the COVID-19 pandemic will disappear, and they’ll be able to host in-person events without updating their HVAC plant. I doubt they’ll be so lucky.
Frankly, I’m surprised that those who have updated their venue ventilation for COVID-19, aren’t publicizing this as a competitive advantage. Our industry is yearning for the return of in-person meetings. Being able to say a property is compliant with current ventilation guidance seems like a great selling point. This article from the Washington Post (kindly shared with me by Joan Eisenstodt) exemplifies the kind of positive PR that’s possible.
After all, many smaller businesses have already taken the necessary steps to create safe ventilation in their buildings. My dentist and physical therapist, and my wife’s massage therapist have all created safe ventilation environments for their places of business. They’re happy to share the details with anyone who asks.
Is it too much to ask meeting venues to do the same?
Here are some additional resources that you may find useful. Again, please be cautious of any information you find that has not been published or updated in the last few months—it may be outdated.
Many thanks to Joan Eisenstodt, Robert Carey, Anne Carey, Barbara McManus, Paul Radde, Dan Cormany, Sarah Diem, and Lauren Siring, who provided information and helpful suggestions and resources as I found my way into the complex topic of venue ventilation for COVID-19!
This April 2021 article includes information I’ve compiled from a variety of current sources. I’ve surely missed some valuable information. Please help me improve and update what I’ve shared via your comments below. Thank you!
Image attribution: medical.mit.edu
About six months ago I noticed that my Apple Watch wasn’t consistently reading my heart rate during running workouts. The watch started displaying “measuring” my heartbeat for minutes (see Figure 1), especially at the beginning of a run. Sometimes the heart rate monitor stopped working to such an extent that I couldn’t even get a few readings during a 25-minute run (see Figure 2). I love my Apple Watch but it was time to fix my Apple Watch heart rate monitor.
After doing some research, here’s what I’ve curated from various internet sources, summarized in one convenient place.
The first thing to determine is whether your watch’s heart rate monitor is working at all!
Check the following settings on your watch.
—On your iPhone, go to Settings > Privacy > Motion & Fitness and check that both Fitness Tracking and Health are On.
—Open your iPhone’s Watch app and:
If any of these settings are incorrect, they will prevent your watch from reading your heart rate during a workout. Set them correctly, and test your watch again.
—Clean the sensors on the back. The two that read your heart rate during exercise are the white LEDs at 3 and 9 o’clock that you may have noticed flashing green from time to time.
—Make sure that the watch is snug on your wrist.
IMPORTANT TIP IF YOU HAVE A MILANESE LOOP WATCH BAND!
I love my Apple Watch Milanese Loop band. But I’ve found that during the day it loosens slightly. So, right before you exercise and before you start the Workout app tighten the band!
—Apple says that cold weather conditions can make reading your heart rate less reliable. If the flakiness of your heart rate monitor seems to be worse on cold days, try wearing warmer clothing on the arm where it’s fastened.
—If your heart rate monitor is still flaky, try the approved Apple resetting options listed here.
[Updated on April 16, 2020] While running today I thought of a workaround that I believe is worth trying.
When you’re not running the Activity app, an Apple Watch only reads your heartbeat every ten minutes. One possibility is that — due to unknown circumstances — during the first few minutes of your exercise, your heart rate is changing too fast for the watch to accurately measure it. Since the watch’s Heart Rate app turns on the constant heart rate monitor, try the following:
Before you start your exercise routine, select the Heart Rate app and wait until it shows you your heart rate before starting the Activity app and your exercise.
Since my watch is now OK I can’t test this, but perhaps it will work for you. Please share your experience in the comments.
I tried all of the suggestions above. However, I was skeptical that any of them would work, because I’d seen a slow degeneration in the reliability of my watch to read my heartbeat while using my watch for the same workout over the same route for months.
I concluded that my watch’s heart rate sensor was defective. Luckily my Apple Watch Series 3 was still covered by AppleCare. I took it to our local Apple Premium Service Provider. As I expected, defective Apple Watches are returned to Apple for repair or replacement. Before sending it back, I unpaired the Watch from my iPhone (important!), which backs up the Watch contents to the phone.
After a week’s turnaround, Apple sent back a new replacement watch. It was a little strange not wearing a watch for a week, and it was interesting to see the limited workout data provided by my iPhone compared to what I was used to from my watch.
I’m happy to report that the replacement watch now works perfectly during my workout. Figure 3 shows the continuous heart rate chart shown by the new watch. And Figure 4 compares typical charts from the old and new watches.
Many people have reported that the heart rate sensors on an Apple Watch have become unreliable. Unfortunately, it seems that watch heart rate sensors can degrade over time, and the various “fixes” suggested online might not always be successful. I was lucky that AppleCare still covered my watch. If you don’t have warranty coverage, I suggest politely pointing out that this defect seems to be widespread, and asking whether Apple will replace your watch anyway. Good luck!
Please feel free to share any other fixes, suggestions, or experiences with this problem you’d like to add in the comments below!