Towards the end of last year, Meta released SAM 3, which stands for the third version of its Segment Anything Model. The way it generally works is that it allows you to detect, edit, and experiment with things in images and videos. For example, if you were looking at a video of a street, you could ask it to find all the scooters (which I did below), count the number of pedestrians wearing black pants, blur all the license plates on the cars, and so on.
Towards the end of last year, Meta released SAM 3, which stands for the third version of its Segment Anything Model. The way it generally works is that it allows you to detect, edit, and experiment with things in images and videos. For example, if you were looking at a video of a street, you could ask it to find all the scooters (which I did below), count the number of pedestrians wearing black pants, blur all the license plates on the cars, and so on.
This is immediately useful for a company like Meta because it allows for object-level modifications across its content creation platforms. So if you took a video of someone dancing and you desperately wanted to give them a bobblehead, SAM 3, I'm told, would allow you to quickly do that. Other AI models, such as Gemini, can also segment, but supposedly the SAM models are better and more precise at this specific task.
Beyond bobblehead videos, the potential of this model seems enormous for real estate, cities, and, of course, many other things. Using the above image as an example, you can quickly imagine SAM 3 being used to count and track modal splits across a city, and then make planning decisions based on real-time data.
People are also using it for real estate purposes. Pair the model with satellite images, and you can ask it to tell you how many houses have a pool, which houses recently had their roof replaced (and have solar panels), how many cars are parked on a street, how many cars are parked at Canadian Tire, and the average building lot coverage in an area.
You could also use it to swap out finishes in a real estate listing (including in videos), and get material/area takeoffs ahead of a construction project. I don't know for sure, but I would also imagine that this model would make a great building condition inspector. Come to think of it, I'd love a SAM 3 that could walk our construction sites and document every little detail!
Of course, a lot of these use cases are already being tackled. But the models are getting that much better. And that will lead to even more innovation.
Cover photo by Above Horizon on Unsplash
Engaging in physical activity is unequivocally associated with improved health outcomes. But are certain physical activities better than others? And what might the implications be for how we design our cities?
Here is a brand new study that examined the relationship between specific types of physical activity and the risk of death, using two large cohort studies with more than 30 years of self-reported data.
The study included information on walking, jogging, running, cycling (including stationary machines), lap swimming, tennis, climbing flights of stairs, rowing, and weight training.
It's important to note that this is an observational study using self-reported data. There are limitations to this. One question mark is around intensity. When someone reports swimming for an hour, it could be vigorous or casual. And the researchers note that long, low-intensity physical activities could bias the observed associations toward the null.
With this caveat out of the way, here's what they found:
Their two key findings were that (1) most physical activities lower mortality rates in a non-linear way when you do more of them, and (2) mixing different physical activities is associated with lower mortality, independent of total activity levels. Variety is good.
Interestingly enough, the most effective activity at lowering overall mortality is the simplest one: walking. It was found to reduce all-cause mortality by about 17%. This is the difference, or maximum observed benefit, between the highest walking group and a sedentary baseline.
Once again, the data clearly shows that walkable cities can help produce meaningfully better health outcomes. So, if, like me, you subscribe to the philosophy that there's no greater luxury in life than our health, well, then there's perhaps no greater luxury than living in a walkable city.
Cover photo by Alain ROUILLER on Unsplash
Back in the fall of 2006, almost twenty years ago, Sam Zell's Equity Office Properties Trust announced that it had entered into a definitive agreement to be acquired by Blackstone Real Estate Partners, in a transaction valued at approximately US$36 billion. This was a massive deal at the time, so much so that Sam Zell would later come to the University of Pennsylvania, where I was in grad school at the time, to talk to real estate students about how smart he was.
The transaction closed in 2007 and, in hindsight, it looked like he had timed the peak of the real estate market perfectly. But in all fairness, when asked about his clairvoyant timing, his response was that he had no idea (probably with a strong expletive somewhere in the middle). His honest answer was that Blackstone simply offered him a price for the portfolio that was greater than their own internal valuation, and so he accepted it.
Another question that he was asked went something like this: "Blackstone is likely going to break up the portfolio, sell off the assets individually or in chunks, and make boatloads of money. Why didn't you just do that?" Despite the peak-market timing, this statement ended up being true. Blackstone generated something like a $7 billion profit on the deal.
But Sam's response was that he couldn't. He cited an esoteric IRS rule that stipulates that once a REIT decides to sell all of its assets and formalizes a liquidation plan, it has a 24-month window to do so, or else get hit with additional corporate taxes. Regardless of the specific IRS section, his reasoning was simple: you never want to be a seller when buyers know you need to sell by a certain time.
This is, of course, intuitively true. Negative leverage is bad in negotiations. In other words, it is highly unlikely that Sam could have generated the same $7 billion profit. I mean, as far as I can tell, Blackstone didn't sell the last office building from the portfolio until 2018, over a decade later.
I was reminded of this principle when reading Prime Minister Carney's speech to the World Economic Forum this week. (This entire post was the best real estate segue I could come up with.) If you haven't read or heard it yet, I would strongly encourage you to do so. Leverage is crucial in negotiations, and it's best to do everything you can to manufacture it.
Cover photo by Kyle Fritz on Unsplash
This is immediately useful for a company like Meta because it allows for object-level modifications across its content creation platforms. So if you took a video of someone dancing and you desperately wanted to give them a bobblehead, SAM 3, I'm told, would allow you to quickly do that. Other AI models, such as Gemini, can also segment, but supposedly the SAM models are better and more precise at this specific task.
Beyond bobblehead videos, the potential of this model seems enormous for real estate, cities, and, of course, many other things. Using the above image as an example, you can quickly imagine SAM 3 being used to count and track modal splits across a city, and then make planning decisions based on real-time data.
People are also using it for real estate purposes. Pair the model with satellite images, and you can ask it to tell you how many houses have a pool, which houses recently had their roof replaced (and have solar panels), how many cars are parked on a street, how many cars are parked at Canadian Tire, and the average building lot coverage in an area.
You could also use it to swap out finishes in a real estate listing (including in videos), and get material/area takeoffs ahead of a construction project. I don't know for sure, but I would also imagine that this model would make a great building condition inspector. Come to think of it, I'd love a SAM 3 that could walk our construction sites and document every little detail!
Of course, a lot of these use cases are already being tackled. But the models are getting that much better. And that will lead to even more innovation.
Cover photo by Above Horizon on Unsplash
Engaging in physical activity is unequivocally associated with improved health outcomes. But are certain physical activities better than others? And what might the implications be for how we design our cities?
Here is a brand new study that examined the relationship between specific types of physical activity and the risk of death, using two large cohort studies with more than 30 years of self-reported data.
The study included information on walking, jogging, running, cycling (including stationary machines), lap swimming, tennis, climbing flights of stairs, rowing, and weight training.
It's important to note that this is an observational study using self-reported data. There are limitations to this. One question mark is around intensity. When someone reports swimming for an hour, it could be vigorous or casual. And the researchers note that long, low-intensity physical activities could bias the observed associations toward the null.
With this caveat out of the way, here's what they found:
Their two key findings were that (1) most physical activities lower mortality rates in a non-linear way when you do more of them, and (2) mixing different physical activities is associated with lower mortality, independent of total activity levels. Variety is good.
Interestingly enough, the most effective activity at lowering overall mortality is the simplest one: walking. It was found to reduce all-cause mortality by about 17%. This is the difference, or maximum observed benefit, between the highest walking group and a sedentary baseline.
Once again, the data clearly shows that walkable cities can help produce meaningfully better health outcomes. So, if, like me, you subscribe to the philosophy that there's no greater luxury in life than our health, well, then there's perhaps no greater luxury than living in a walkable city.
Cover photo by Alain ROUILLER on Unsplash
Back in the fall of 2006, almost twenty years ago, Sam Zell's Equity Office Properties Trust announced that it had entered into a definitive agreement to be acquired by Blackstone Real Estate Partners, in a transaction valued at approximately US$36 billion. This was a massive deal at the time, so much so that Sam Zell would later come to the University of Pennsylvania, where I was in grad school at the time, to talk to real estate students about how smart he was.
The transaction closed in 2007 and, in hindsight, it looked like he had timed the peak of the real estate market perfectly. But in all fairness, when asked about his clairvoyant timing, his response was that he had no idea (probably with a strong expletive somewhere in the middle). His honest answer was that Blackstone simply offered him a price for the portfolio that was greater than their own internal valuation, and so he accepted it.
Another question that he was asked went something like this: "Blackstone is likely going to break up the portfolio, sell off the assets individually or in chunks, and make boatloads of money. Why didn't you just do that?" Despite the peak-market timing, this statement ended up being true. Blackstone generated something like a $7 billion profit on the deal.
But Sam's response was that he couldn't. He cited an esoteric IRS rule that stipulates that once a REIT decides to sell all of its assets and formalizes a liquidation plan, it has a 24-month window to do so, or else get hit with additional corporate taxes. Regardless of the specific IRS section, his reasoning was simple: you never want to be a seller when buyers know you need to sell by a certain time.
This is, of course, intuitively true. Negative leverage is bad in negotiations. In other words, it is highly unlikely that Sam could have generated the same $7 billion profit. I mean, as far as I can tell, Blackstone didn't sell the last office building from the portfolio until 2018, over a decade later.
I was reminded of this principle when reading Prime Minister Carney's speech to the World Economic Forum this week. (This entire post was the best real estate segue I could come up with.) If you haven't read or heard it yet, I would strongly encourage you to do so. Leverage is crucial in negotiations, and it's best to do everything you can to manufacture it.
Cover photo by Kyle Fritz on Unsplash
Share Dialog
Share Dialog
Share Dialog
Share Dialog
Share Dialog
Share Dialog
