Wait, isn't the Bernoulli effect thing they're demoing now wrong? I thought that was a "common misconception" and wings don't really work by the "longer path" that air takes over the top, and that it was more about angle of attack (which is why planes can fly upside down).
It seems like it's actually an ideal "trick" question for an LLM actually, since so much content has been written about it incorrectly. I thought at first they were going to demo this to show that it knew better, but it seems like it's just regurgitating the same misleading stuff. So, not a good look.
Yeah, they sure clicked away from it very fast and kept adjusting the scrollbars. It was confusing what it was trying to display. Furthermore, the prompt contained "Canvas" and "SVG" while as someone with webdev experience these are certainly familiar concepts, i wouldn't consider those in the "casual lexicon" for a random user trying to help a middle schooler with homework. I'm not impressed...
IMO Claude 3.7 could have done a similar / better job with that a year ago.
Seems like sheer incompetence, I’m sure at least the top quintile of my junior year fluid dynamics class could notice it was fishy within a 15 minute meeting… probably more than half could.
The last part of GPT's answer does say:
"Bernoulli's effect works alongside Newton's Third Law - the wing pushes air downward [...] - so the lift isn't only Bernoulli..."
According to this answer on physics stackexchange, Bernoulli accounts for 20% of the lift, so GPT's answer seems about right:
https://physics.stackexchange.com/a/77977
That's still not particularly usefully accurate: it's not a split between the effects, they're the same thing viewed through different lenses. You could, perhaps, say that an airfoil gets X% more lift than a flat plate at a given angle of attack, but the flat plate also 'gets lift through Bernoulli', it's just not as obvious exactly why the flows are faster on the top (and the common 'the air needs to transit the wing in an equal time on top and bottom' is an incorrect rule, and in practice broken by most wings)
All things that create lift, lift the wings—and you need them all for efficient flight. The Bernoulli effect is one thing, but does not produce the main lift force in many circumstances.
Aircraft with symmetrical wings fly just fine, and most aircraft can fly upside down. So you don't need the Bernoulli effect. Exploiting all the effects gives you more efficient planes though
That said, I recall reading somewhere that it's a combination of effects, and the Bernoulli effect contributes, among many others. Never heard an explanation that left me completely satisfied, though. The one about deflecting air down was the one that always made sense to me even as a kid, but I can't believe that would be the only explanation - there has to be a good reason that gave rise to the Bernoulli effect as the popular explanation.
And you can tell that effect makes some sense of you hold a sheet of paper and blow air over it - it will rise. So any difference in air speed has to contribute.
What is just plain wrong is the equal transit time thing, people saying that air on both sides of the wing have to take the same time to pass it.
The Bernoulli effect as a separate entity is really a result of (over)simplification, but it's not wrong. You need to solve the Navier-Stokes equations for the flow around the wing, but there are many ways to simplify this - from CFD at different resolutions, via panel methods and potential theory, to just conservation of energy (which is the Bernoulli equation). So it gets popularized because it's the most simplified model.
To give an analogy, you can think of all CPUs as a von Neumann architecture. But the reality is that you have a hugely complicated thing with stacks, multiple cache levels, branch predictors, specex, yada yada.
On the very fundamental level, wings make air go down, and then airplane goes up. Just like you say. By using a curved airfoil instead of a flat plate, you can create more circulation in the flow, and then because of the way fluids flow you can get more lift and less drag.
Imagine an airfoil with a super tall square block on top of it. Due to equal transit time, the particles must accelerate to relativistic speeds to reach the end to rejoin the lower surface particles, when I point a house fan at it. We have created a magical flow accelerator!
I believe the deflection is the high-level explanation. Things like the Bernoulli effect and the air on the top of the airfoil travelling faster (it does -- far faster than the equal transit time theory implies actually), are the "instantiation" or outcomes of the air deflection. This is my understanding. Hence airplanes can fly upside down because even if the airfoil is upside down, it's still deflecting the air, just perhaps less efficiently (I think it's true that planes flying upside down need a more extreme angle of attack to maintain lift, so this makes sense)
It seems like it's actually an ideal "trick" question for an LLM actually, since so much content has been written about it incorrectly. I thought at first they were going to demo this to show that it knew better, but it seems like it's just regurgitating the same misleading stuff. So, not a good look.