Describe a universal way of encoding a 3d image (example: x,y, contents) into a 2d message (sequence, intensity; a binary sequence is the simplest method), without making noncommunicable assumptions such as left-to-right.
Alternately, describe how to decode a self-documenting encoding of any type, using any means except knowing the encoding.
You receive a signal flashed in two color channels. Both off, I’ll show as space, and for a lot of space, return. One on is 1, the other on is 2, and both on is 3. You receive:
Can I ask for a minor correction on the line that says: “11 3211 101 32 1111”—you’ve not defined what 0 means, so is it meant to be a space or a 2 instead? (probably the latter) Thanks.
ETA: I think the line above it may have a minor mistake too, “122212111211221” bhtug or gur bgure jnl nebhaq?
ETA2: I think a second problem with 33112221121 in the penultimate line—one of the ones should be missing I think. If I’m wrong I’ve probably messed up my interpretation
Added a few more lines. By including only the things I could do off the top of my head, I restricted myself to too-small numbers and gave you the wrong idea.
That can be simplified to the level of illumination of Io and Ganymede as seen from Triton, accounting for all eclipses (probably not literally, but there are natural phenomena which produce patterns at least as interesting; see pulsars).
Since it’s more likely that a natural phenomenon created this pattern of observations than that positional notation and time-ordering are shared by a given ETI, I would observe and try to understand the natural system which created this pattern.
It may be worth catching up on the prior art here. Hans Freudenthal’s LINCOS) was developed as a method of communicating with aliens of any sort, using nothing but radio pulses.
That gets you from ‘encoding’ to ‘communication’. When the other intelligence is looking at things other than the duration and magnitude of your EM pulses, they can’t decode the rest.
The hard step is only in establishing the very first few conventions, after that it becomes trivial.
Take a binary-colored picture of a circle (outline only), on a square background. Just transmit one line after the next (all appended), for linebreaks use a sequence that doesn’t otherwise occur, e.g. ’11′. Every optimizer worth its salt should figure out that the least complex / most compressible representation of that overall pattern will be to break up the transmission at those linebreaks such that the ’1’s representing the circle are close to each other, forming a circle.
Vary with various image sizes, to establish that point. Since it’s symmetrical, left-to-right and right-to-left doesn’t matter. Then you can start transmitting various black and white pictures of stars and their spectra, assigning other encodings to them (if you insist on colors).
There may be a surprise if the whole time the aliens thought the pictures were meant to be interpreted upside down, and wonder why you’re not standing on your head when they meet us. But the gist should get through.
There may be a surprise if the whole time the aliens thought the pictures were meant to be interpreted upside down, and wonder why you’re not standing on your head when they meet us. But the gist should get through.
If, once you finally meet, the alien greets you and holds out his left hand to shake… do not touch it!
“We are happy to assist with the creation of many more humans using this nuclear weapon. We know that sadly they will eventually all perish in a female’s womb, having shriveled away into nothing.”
The first convention is that the sequence is coded by flashes of intensity distinct in time with a beginning and end. (rather than the information being the Fourier transform of the light wave, or any other property of light).
Once we have established what 1 and 0 are, how to decode an ordered string of them, and that we are drawing a picture with a bitmap (as opposed to a vector encoding, or an image encoding foreign to human computer science), we have to establish that we are using scanlines (as opposed to any other way of ordering a bitmap). We also need a line break sequence which is guaranteed to never occur outside a line break; that means that the line break pattern has to be a sequence of bits which cannot occur within the line. (not ‘doesn’t occur in this particular image’) That requirement breaks any simple binary encoding.
Something as simple as transmitting the image using a different order for the pixels, like a spiral on a hexagonal grid, would be difficult to decode. Something complicated, like encoding the message into a transform of the wave or an interference pattern of two waves, would be impossible to notice even if the sending civilization was using electromagnetic radiation to send their message.
I’m also not sure why an image of a particular star or geometric figure would be first; I’d transmit the cosmic background radiation as the first image. That allows the receiver to use their own observations to confirm their understanding of our encoding.
Sending strange patterns on the same frequency is a good way to assure that our signal—if received—gets classified as ‘generated by an unknown phenomenon’. Unless we’re transmitting on many frequencies or change the amplitude (signal strength), the Fourier transform would just yield a single number. If all we vary are the times between bursts, it should be quite clear that the information lies somewhere in the time between bursts. I’m no expert in this, though (shrug).
We also need a line break sequence which is guaranteed to never occur outside a line break; that means that the line break pattern has to be a sequence of bits which cannot occur within the line. (not ‘doesn’t occur in this particular image’) That requirement breaks any simple binary encoding.
You’re thinking about establishing the final encoding that can be used for all subsequent communications, but that’s not necessary. These aren’t the Golden Plates which need to contain everything we’ll “ever” communicate (although their approach is relevant to our discussion, it’s a different scenario).
The one thing that (nearly?) any optimizer should be able to do (to ever have evolved in the first place) is to notice patterns in its environment, and to have a tendency to compress those patterns into their simplest representations (model building). Only when arranging the lines such that a circle (and a line on one side representing the ’11′ line breaks) emerges is the pattern simplest to describe.
At some later point we can still move to a more sophisticated line break representation, slowly varying the encoding of that baseline calibration picture, we could even keep the ’11′ for nostalgia’s sake.
I’m also not sure why an image of a particular star or geometric figure would be first;
Using cosmic background radiation introduces new elements to be figured out (e.g. how you visualize frequencies). Anyways, we’re not bandwidth limited in any meaningful sense, so there’s no need to rush things. (Re: circle—see above)
How are you modulating a carrier wave if you aren’t varying frequency or amplitude?
Would you notice a transmission which consisted of a constant illumination equivalent to that produced by a number of lasers with frequencies that were linked to powers of two? Instead of “On, on, off, off, on, off” separated by time, there would be a single signal which would scope to the same wave as “sin(x)+sin(2x)+sin(16x)” or “”sin(x)+1/2sin(2x)+1/16sin(16x)”
Meanwhile, because we’re broadcasting AM broadcasts on many different frequencies, they’re trying to figure out a:Why and how our transmitter is failing intermittently on such a fast scale b:What our baseline frequency is. c:How to decode the vast wealth of information they have.
If all we do is notice patterns and automatically ascribe meaning to them, we end up looking at pulsars. For that matter, what evidence do we have that pulsars aren’t the result of intelligent communication? Can you construct a ‘universal’ encoding which could be communicated using only the properties of pulsars? Could you decode such an encoding?
Describe a universal way of encoding a 3d image (example: x,y, contents) into a 2d message (sequence, intensity; a binary sequence is the simplest method), without making noncommunicable assumptions such as left-to-right.
Alternately, describe how to decode a self-documenting encoding of any type, using any means except knowing the encoding.
You receive a signal flashed in two color channels. Both off, I’ll show as space, and for a lot of space, return. One on is 1, the other on is 2, and both on is 3. You receive:
21 31221 1
1 32 21 31221 21
21 32 21 31221 221
11 32 21 31221 2221
221 32 21 31221 22221
121 32 21 31221 222221
211 32 21 31221 2222221
111 32 21 31221 22222221
2221 32 21 31221 222222221
1111 32 21 31221 2222222222222221
111 32 11 32 221
2121121 32 121221 32 121211
1 31 1 32 21
121221 31 121211 32 2121121
2
2 3211 1
2 3211 21
2 3211 11
2 3211 221
2 3211 121
2 3211 211
2 3211 111
2 3211 122212111211221
2 3211 122112221212111
1 3211 1 32 1
11 3211 121 32 1111
11 3211 21 31 1 32 111
11 31 21 3211 1 32 121
2 32221 21 32 1
1 32221 21 32 21
21 32221 21 32 221
11 32221 21 32 2221
21 32221 11 32 1221
221 32221 21 32 22221
221 32221 11 32 1222121
21 32221 11 3211 21 32 21221
21 3211 11 32221 21 32 2222221
21 32221 111 3211 1211 31 1221 32
What do you reply?
Assuming you got that, there’s more...
312221 12221121 111 3312221121 32 111
111 32 3312221121
312221 12221121 121 3312221121 32 121
111 32 3312221121 32 21
322221 12221121 3332 3312221121 32 3312221121 3331
322221 12221121 3332 2 3211 3312221121 3331
322221 12221121 212211 3332 3332 3312221121 31 33212211 3331 32 3332 33212211 31 3312221121 3331 3331
322221 12121 3332 21 32221 3312121 32 3332 21 32221 3332 3312121 32 1 3331 3331
Shouldn’t these lines
111 32 11 32 221
2121121 32 121221 32 121211
be
111 32 11 31 221
2121121 32 121221 31 121211
? Or do I misunderstand? [Edit: I misunderstood :) — never mind.]
Also, the last line of the first part seems ambiguous, since gur beqre bs bcrengvbaf unf abg orra rfgnoyvfurq nf sne nf v pna frr.
11 3211 21 31 1 32 111
11 31 21 3211 1 32 121
21 32221 11 3211 21 32 21221
21 3211 11 32221 21 32 2222221
Do you mean
?
21 32221 11 3211 21 32 21221
I think that you, like I, just messed up the arithmetic there.
Can I ask for a minor correction on the line that says: “11 3211 101 32 1111”—you’ve not defined what 0 means, so is it meant to be a space or a 2 instead? (probably the latter) Thanks.
ETA: I think the line above it may have a minor mistake too, “122212111211221” bhtug or gur bgure jnl nebhaq?
ETA2: I think a second problem with 33112221121 in the penultimate line—one of the ones should be missing I think. If I’m wrong I’ve probably messed up my interpretation
Your first and third corrections are right (and doh! Slippy fingers!)
The second stands. I’ve added another line there.
Vs V’z evtug naq gung frpgvba vf nobhg cevzrf, gurfr ahzoref pna bayl or qrpvcurerq nf cevzrf vs gur beqrevat jnf ovt-raqvna (zbfg fvtavsvpnag qvtvg svefg), nf vg’f va uhzna hfntr bs Nenovp ahzrenyf—ohg va gur erfg bs gur pbagrag lbh tvir, nyy gur bgure ahzoref zhfg or qrpvcurerq va yvggyr-raqvna beqre (yrnfg fvtavsvpnag qvtvg svefg)...
Thanks for the puzzle btw, it’s great fun. I’ll continue working on it tomorrow (it’s getting late where I live). :-)
Added a few more lines. By including only the things I could do off the top of my head, I restricted myself to too-small numbers and gave you the wrong idea.
Please don’t give answer just yet, I’ve solved parts of it and I think I’m close to solving rest of it as well.
That can be simplified to the level of illumination of Io and Ganymede as seen from Triton, accounting for all eclipses (probably not literally, but there are natural phenomena which produce patterns at least as interesting; see pulsars).
Since it’s more likely that a natural phenomenon created this pattern of observations than that positional notation and time-ordering are shared by a given ETI, I would observe and try to understand the natural system which created this pattern.
Doubtful.
It may be worth catching up on the prior art here. Hans Freudenthal’s LINCOS) was developed as a method of communicating with aliens of any sort, using nothing but radio pulses.
That gets you from ‘encoding’ to ‘communication’. When the other intelligence is looking at things other than the duration and magnitude of your EM pulses, they can’t decode the rest.
The hard step is only in establishing the very first few conventions, after that it becomes trivial.
Take a binary-colored picture of a circle (outline only), on a square background. Just transmit one line after the next (all appended), for linebreaks use a sequence that doesn’t otherwise occur, e.g. ’11′. Every optimizer worth its salt should figure out that the least complex / most compressible representation of that overall pattern will be to break up the transmission at those linebreaks such that the ’1’s representing the circle are close to each other, forming a circle.
Vary with various image sizes, to establish that point. Since it’s symmetrical, left-to-right and right-to-left doesn’t matter. Then you can start transmitting various black and white pictures of stars and their spectra, assigning other encodings to them (if you insist on colors).
There may be a surprise if the whole time the aliens thought the pictures were meant to be interpreted upside down, and wonder why you’re not standing on your head when they meet us. But the gist should get through.
If, once you finally meet, the alien greets you and holds out his left hand to shake… do not touch it!
“We are happy to assist with the creation of many more humans using this nuclear weapon. We know that sadly they will eventually all perish in a female’s womb, having shriveled away into nothing.”
The first convention is that the sequence is coded by flashes of intensity distinct in time with a beginning and end. (rather than the information being the Fourier transform of the light wave, or any other property of light).
Once we have established what 1 and 0 are, how to decode an ordered string of them, and that we are drawing a picture with a bitmap (as opposed to a vector encoding, or an image encoding foreign to human computer science), we have to establish that we are using scanlines (as opposed to any other way of ordering a bitmap). We also need a line break sequence which is guaranteed to never occur outside a line break; that means that the line break pattern has to be a sequence of bits which cannot occur within the line. (not ‘doesn’t occur in this particular image’) That requirement breaks any simple binary encoding.
Something as simple as transmitting the image using a different order for the pixels, like a spiral on a hexagonal grid, would be difficult to decode. Something complicated, like encoding the message into a transform of the wave or an interference pattern of two waves, would be impossible to notice even if the sending civilization was using electromagnetic radiation to send their message.
I’m also not sure why an image of a particular star or geometric figure would be first; I’d transmit the cosmic background radiation as the first image. That allows the receiver to use their own observations to confirm their understanding of our encoding.
Sending strange patterns on the same frequency is a good way to assure that our signal—if received—gets classified as ‘generated by an unknown phenomenon’. Unless we’re transmitting on many frequencies or change the amplitude (signal strength), the Fourier transform would just yield a single number. If all we vary are the times between bursts, it should be quite clear that the information lies somewhere in the time between bursts. I’m no expert in this, though (shrug).
You’re thinking about establishing the final encoding that can be used for all subsequent communications, but that’s not necessary. These aren’t the Golden Plates which need to contain everything we’ll “ever” communicate (although their approach is relevant to our discussion, it’s a different scenario).
The one thing that (nearly?) any optimizer should be able to do (to ever have evolved in the first place) is to notice patterns in its environment, and to have a tendency to compress those patterns into their simplest representations (model building). Only when arranging the lines such that a circle (and a line on one side representing the ’11′ line breaks) emerges is the pattern simplest to describe.
At some later point we can still move to a more sophisticated line break representation, slowly varying the encoding of that baseline calibration picture, we could even keep the ’11′ for nostalgia’s sake.
Using cosmic background radiation introduces new elements to be figured out (e.g. how you visualize frequencies). Anyways, we’re not bandwidth limited in any meaningful sense, so there’s no need to rush things. (Re: circle—see above)
How are you modulating a carrier wave if you aren’t varying frequency or amplitude?
Would you notice a transmission which consisted of a constant illumination equivalent to that produced by a number of lasers with frequencies that were linked to powers of two? Instead of “On, on, off, off, on, off” separated by time, there would be a single signal which would scope to the same wave as “sin(x)+sin(2x)+sin(16x)” or “”sin(x)+1/2sin(2x)+1/16sin(16x)”
Meanwhile, because we’re broadcasting AM broadcasts on many different frequencies, they’re trying to figure out
a:Why and how our transmitter is failing intermittently on such a fast scale
b:What our baseline frequency is.
c:How to decode the vast wealth of information they have.
If all we do is notice patterns and automatically ascribe meaning to them, we end up looking at pulsars. For that matter, what evidence do we have that pulsars aren’t the result of intelligent communication? Can you construct a ‘universal’ encoding which could be communicated using only the properties of pulsars? Could you decode such an encoding?