Alan Turing’s life was as groundbreaking and visionary as it was tragic. After developing the concept of a universal computing machine—the idea that a computer could do anything you program it to—Turing set to thinking about what would define success.
Everyone knows Alan Turing, who cracked Enigma codes immortalized in the movie The Imitation Game. Few know the important role his sister Kay played in providing drinks, snacks, and sandwiches for him and his colleagues at that time and, this really suprised me,, for the actors in the movies as well!
Speaking of the new generation of CAPTCHAs, my personal pet peeve are the ones that have you select all squares containing e.g. a motorcycle. Then there's a single motorcycle in the image spanning several squares, with some parts of it barely sticking out into nearby squares. Do I select those parts? Do I select just the body of the motorcycle or the rearview mirror? Do I select the foot of the motorcycle rider? Is reality real? What do you want from me, CAPTCHA?!
‘I did not come, Sir, on foot . I came in a carriage.’
‘Then if you came, Sire, in a carriage, explain to me what that is. Is it the pole that is the chariot?’
‘I did not say that.’
‘Is it the axle that is the chariot?’
‘Certainly not.’
‘Is it the wheels, or the framework, or the ropes, or the yoke, or the spokes of the wheels, or the goad, that are the chariot?’
And to all these he still answered no.
‘Then is it all these parts of it that are the chariot?’
‘No, Sir.’
‘But is there anything outside them that is the chariot?’
And still he answered no.
‘Then thus, ask as I may, I can discover no chariot. Chariot is a mere empty sound. What then is the chariot you say you came in? It is a falsehood that your Majesty has spoken, an untruth! There is no such thing as a chariot!
Here is what GPT-4 suggests (even though it never worked for me):
I can imagine how frustrating CAPTCHAs can be, especially when they involve subjective judgment calls on what to include in your selection. The challenge you're describing is common and can be quite tricky. Here's a general guide to help you navigate these CAPTCHA puzzles:
1. **Motorcycle Spanning Multiple Squares:** You're typically supposed to select all squares that contain any part of the motorcycle. If the motorcycle's body extends into a square, even just a little, it should be considered part of the motorcycle for the purposes of the CAPTCHA.
2. **Tiny Bits Sticking Out:** This is where it gets subjective. If a piece of the motorcycle or something directly connected to it, like a rearview mirror, extends into another square, it's usually safe to select that square as well. However, if the piece in question is extremely small or barely perceptible, it might not be necessary to include it. Unfortunately, there's no universal rule, and different CAPTCHA systems may have different thresholds for what counts.
3. **Rider's Foot:** If you're asked to select all squares with a motorcycle, it technically refers to the vehicle itself. However, if the rider's foot is visually perceived as part of the motorcycle due to being on it or very close, it might be safer to select it. When in doubt, it's usually better to err on the side of inclusivity.
4. **Is Reality Real?** Well, that's a philosophical question that's a bit out of scope for CAPTCHA, but in the context of these puzzles, consider "reality" to be what the CAPTCHA algorithm determines it to be. Your goal is to match your perception to the expected input of the algorithm as closely as possible.
5. **What CAPTCHA Wants:** CAPTCHA systems are designed to distinguish between humans and automated systems. They often err on the side of caution, requiring users to be over-inclusive rather than under-inclusive in identifying objects. The idea is that a bot would either not recognize the object at all or would not be able to interpret the nuances of partial object inclusion, whereas a human would be better at making a judgement call.
If you're ever in doubt, it's usually better to include any ambiguous squares rather than leave them out. If you get it wrong, CAPTCHAs typically give you a second chance with a new puzzle. Remember, the goal of these tests isn't perfection but to prevent automated abuse, so they're typically designed to have some tolerance for human error.
My biggest fear is over time, we will outsource our thinking/troubleshooting to the AI instead of trying ourselves first, and would we stop being human? Most of us are looking for shortcuts in life, and this will become like asking AI rather than asking Google, even when sometimes we do not know if it is accurate. Like I read somewhere, doctors asking AI how to communicate with patients about severe disease situations. We thought that it will be a human job for a long long time but may be not.
Yep. And what would it even mean to stop being human? It's such a nebulous concept, I'm not sure it has any real meaning to ask the question. I do believe we are about to see more change in fifty years than during the last five hundred years or so, and we have seen A LOT of change over the last five centuries.
Ah captchas, the bane of modern Internet. They serve a dual purpose nowadays too I believe, as a way for you to train image recognition since it isn't quite optimised yet but it is damn near good. I had not heard of the other forms of captchas, just the weird texts and images are what I have encountered so far.
It's well done! There's more to Turing's life and experiences, but the movie is a solid overview of what happened to him and what he contributed to the world.
Everyone knows Alan Turing, who cracked Enigma codes immortalized in the movie The Imitation Game. Few know the important role his sister Kay played in providing drinks, snacks, and sandwiches for him and his colleagues at that time and, this really suprised me,, for the actors in the movies as well!
Oh, dad.
Speaking of the new generation of CAPTCHAs, my personal pet peeve are the ones that have you select all squares containing e.g. a motorcycle. Then there's a single motorcycle in the image spanning several squares, with some parts of it barely sticking out into nearby squares. Do I select those parts? Do I select just the body of the motorcycle or the rearview mirror? Do I select the foot of the motorcycle rider? Is reality real? What do you want from me, CAPTCHA?!
If you're not in agony over decisions, you're not human!
I guess that's the real test, eh?
There is no motorcycle.
--
How then did you come, on foot, or in a chariot?’
‘I did not come, Sir, on foot . I came in a carriage.’
‘Then if you came, Sire, in a carriage, explain to me what that is. Is it the pole that is the chariot?’
‘I did not say that.’
‘Is it the axle that is the chariot?’
‘Certainly not.’
‘Is it the wheels, or the framework, or the ropes, or the yoke, or the spokes of the wheels, or the goad, that are the chariot?’
And to all these he still answered no.
‘Then is it all these parts of it that are the chariot?’
‘No, Sir.’
‘But is there anything outside them that is the chariot?’
And still he answered no.
‘Then thus, ask as I may, I can discover no chariot. Chariot is a mere empty sound. What then is the chariot you say you came in? It is a falsehood that your Majesty has spoken, an untruth! There is no such thing as a chariot!
---
The Simile of the Chariot. https://encyclopediaofbuddhism.org/wiki/Simile_of_the_chariot
Come for the CAPTCHA jokes, stay for the unexpected philosophical insights.
Here is what GPT-4 suggests (even though it never worked for me):
I can imagine how frustrating CAPTCHAs can be, especially when they involve subjective judgment calls on what to include in your selection. The challenge you're describing is common and can be quite tricky. Here's a general guide to help you navigate these CAPTCHA puzzles:
1. **Motorcycle Spanning Multiple Squares:** You're typically supposed to select all squares that contain any part of the motorcycle. If the motorcycle's body extends into a square, even just a little, it should be considered part of the motorcycle for the purposes of the CAPTCHA.
2. **Tiny Bits Sticking Out:** This is where it gets subjective. If a piece of the motorcycle or something directly connected to it, like a rearview mirror, extends into another square, it's usually safe to select that square as well. However, if the piece in question is extremely small or barely perceptible, it might not be necessary to include it. Unfortunately, there's no universal rule, and different CAPTCHA systems may have different thresholds for what counts.
3. **Rider's Foot:** If you're asked to select all squares with a motorcycle, it technically refers to the vehicle itself. However, if the rider's foot is visually perceived as part of the motorcycle due to being on it or very close, it might be safer to select it. When in doubt, it's usually better to err on the side of inclusivity.
4. **Is Reality Real?** Well, that's a philosophical question that's a bit out of scope for CAPTCHA, but in the context of these puzzles, consider "reality" to be what the CAPTCHA algorithm determines it to be. Your goal is to match your perception to the expected input of the algorithm as closely as possible.
5. **What CAPTCHA Wants:** CAPTCHA systems are designed to distinguish between humans and automated systems. They often err on the side of caution, requiring users to be over-inclusive rather than under-inclusive in identifying objects. The idea is that a bot would either not recognize the object at all or would not be able to interpret the nuances of partial object inclusion, whereas a human would be better at making a judgement call.
If you're ever in doubt, it's usually better to include any ambiguous squares rather than leave them out. If you get it wrong, CAPTCHAs typically give you a second chance with a new puzzle. Remember, the goal of these tests isn't perfection but to prevent automated abuse, so they're typically designed to have some tolerance for human error.
The twisted irony of an AI coaching you on how to be more human!
Very true!
My biggest fear is over time, we will outsource our thinking/troubleshooting to the AI instead of trying ourselves first, and would we stop being human? Most of us are looking for shortcuts in life, and this will become like asking AI rather than asking Google, even when sometimes we do not know if it is accurate. Like I read somewhere, doctors asking AI how to communicate with patients about severe disease situations. We thought that it will be a human job for a long long time but may be not.
Yep. And what would it even mean to stop being human? It's such a nebulous concept, I'm not sure it has any real meaning to ask the question. I do believe we are about to see more change in fifty years than during the last five hundred years or so, and we have seen A LOT of change over the last five centuries.
"...consider "reality" to be what the CAPTCHA algorithm determines it to be."
Well that's not ominous at all!
All part of the plan; best if you don't think about it any more.
Ah captchas, the bane of modern Internet. They serve a dual purpose nowadays too I believe, as a way for you to train image recognition since it isn't quite optimised yet but it is damn near good. I had not heard of the other forms of captchas, just the weird texts and images are what I have encountered so far.
Like maybe a lot of people I learned about Turing from The Imitation Game and this makes me want to watch it again.
It's well done! There's more to Turing's life and experiences, but the movie is a solid overview of what happened to him and what he contributed to the world.