I've been building out a sort of "clickwise"[1] for agents to talk to each other without resorting to English as a communication format.
My problem is approximately ~2000 rules in various levels of conditional nesting from a central context agent to the execution side of things.
This is a better worked example than my confused mess of financial rules.
The structure is a bit more fleshed out, but you are still sending across data which is hard to decipher for a human, but perfect for a machine to bootstrap and learn a set of nested rules about the task.
Finance is a bit less consistent than chess on the rules, but packing into binary "Telepathy" protocols is going to be the next big thing for multi-agent orchestration.
Why does the first frame contain 0, 1, 2, 3, 4, 7, 8 and 15 _twice_? It says something about leading zeroes, but visually that makes no difference. Why isn't this room used to put _all_ the values from 0 to 15 so that there's no implied question of why were those numbers chosen and no others and does that have meaning or not?
Might sound like a nitpick but an arrow is shared visual language. It's based on a literal arrow. There's no reason to think an alien would know what an arrow means.
So essentially, digital trasmission is used to emulate a 2048x2048 sheet of paper and send 32 images, interleaved temporally, with pictograms teaching aliens to decode a bytestream containing glyphs, animations, quiz pages and chess positions. I regret spending time on this.
CRC-32C is the name used in the human walkthrough. The message itself shows the calculation. The intention is for the reader to reconstruct that procedure from the example.
I built Golden Board, a 512 KiB binary message designed to teach chess to an unknown recipient without shared language, culture, or prior knowledge of the game.
The project is inspired by a tradition of messages designed for an unknown intelligence such as Voyager Golden Record, Lincos and others.
But instead of sharing science or art, it teaches chess.
Why chess? Because a small set of rules opens up an enormous world of ideas and beauty. We can teach it from scratch and then let the recipient explore a rich legacy shaped by centuries of human ingenuity, sacrifices, and moments of brilliance.
The message begins by teaching the recipient to count, recognize bytes, and gradually decode and understand everything that follows.
I tested it extensively, using LLMs to simulate an unknown recipient and carefully checking each part of the message. Of course, LLMs are far from perfect stand-ins, but those experiments helped me identify ambiguities and improve the design.
The project is an attempt to solve a broader problem: its bootstrap is chess-agnostic and designed to decode other structured messages. Anyone is welcome to build on it and create messages that teach something entirely different.
Astra didn't even go through the bootstrapping here, it printed samples of the file, noted that "the repeated eight-symbol rows may describe a board game". Found the region borders, then checked positions and sequences vs chess rules, confirmed it was chess, while naming famous moves and openings (Nimzo-Indian opening etc). Then noted "The next target is the bootstrap and program-like structures around the games".
I had tried to pass it off as a "we've received this transmission from deep space" sort of scenario.
Ha, I immediately downloaded the binary and handed it to Fable 5.2 (Medium) before I saw you had already tested it that way. It correctly decoded it in about 10 minutes. Well done, very cool project!
Heh, alongside the documented trials, I’ve been giving other models the raw message and asking them to approach it as an unfamiliar recipient, with zero hints. I’ve had successful decodes that way too. Of course, LLMs know a great deal about chess, but still it’s encouraging to see it work
I've been building out a sort of "clickwise"[1] for agents to talk to each other without resorting to English as a communication format.
My problem is approximately ~2000 rules in various levels of conditional nesting from a central context agent to the execution side of things.
This is a better worked example than my confused mess of financial rules.
The structure is a bit more fleshed out, but you are still sending across data which is hard to decipher for a human, but perfect for a machine to bootstrap and learn a set of nested rules about the task.
Finance is a bit less consistent than chess on the rules, but packing into binary "Telepathy" protocols is going to be the next big thing for multi-agent orchestration.
[1] - https://www.penny-arcade.com/story/automata/automata/automat...
Why does the first frame contain 0, 1, 2, 3, 4, 7, 8 and 15 _twice_? It says something about leading zeroes, but visually that makes no difference. Why isn't this room used to put _all_ the values from 0 to 15 so that there's no implied question of why were those numbers chosen and no others and does that have meaning or not?
Using all 16 values is a reasonable alternative.
The repetition is meant to show that 0011 and 00000011 represent the same quantity. There’s no hidden meaning in the omitted numbers.
Might sound like a nitpick but an arrow is shared visual language. It's based on a literal arrow. There's no reason to think an alien would know what an arrow means.
Fair, but I don't assume the arrow convention is universally understood.
The idea is that it's meaning can be learned from the 5th frame and later reinforced through repetition in other patterns.
Would be fun if it was posted without context as some kind of internet mystery.
I thought of that, but models like Claude or GPT can crack it in a matter of minutes, so it wouldn't be much of a mystery today ┐(´ー`)┌
Am I wrong to immediately think of Contact?
Haha, I'm glad someone brought it up, because a project like this has been my dream since I was 12, when I first saw the movie
So essentially, digital trasmission is used to emulate a 2048x2048 sheet of paper and send 32 images, interleaved temporally, with pictograms teaching aliens to decode a bytestream containing glyphs, animations, quiz pages and chess positions. I regret spending time on this.
[flagged]
"Golden Board uses CRC-32C for this calculation." Pretty sure an extraterrestrial wouldn't be able to rederive CRC-32 without more info.
CRC-32C is the name used in the human walkthrough. The message itself shows the calculation. The intention is for the reader to reconstruct that procedure from the example.
I built Golden Board, a 512 KiB binary message designed to teach chess to an unknown recipient without shared language, culture, or prior knowledge of the game.
The project is inspired by a tradition of messages designed for an unknown intelligence such as Voyager Golden Record, Lincos and others.
But instead of sharing science or art, it teaches chess.
Why chess? Because a small set of rules opens up an enormous world of ideas and beauty. We can teach it from scratch and then let the recipient explore a rich legacy shaped by centuries of human ingenuity, sacrifices, and moments of brilliance.
The message begins by teaching the recipient to count, recognize bytes, and gradually decode and understand everything that follows.
I tested it extensively, using LLMs to simulate an unknown recipient and carefully checking each part of the message. Of course, LLMs are far from perfect stand-ins, but those experiments helped me identify ambiguities and improve the design.
The project is an attempt to solve a broader problem: its bootstrap is chess-agnostic and designed to decode other structured messages. Anyone is welcome to build on it and create messages that teach something entirely different.
Source code and docs: https://github.com/arlegotin/golden-board
Astra didn't even go through the bootstrapping here, it printed samples of the file, noted that "the repeated eight-symbol rows may describe a board game". Found the region borders, then checked positions and sequences vs chess rules, confirmed it was chess, while naming famous moves and openings (Nimzo-Indian opening etc). Then noted "The next target is the bootstrap and program-like structures around the games".
I had tried to pass it off as a "we've received this transmission from deep space" sort of scenario.
Ha, I immediately downloaded the binary and handed it to Fable 5.2 (Medium) before I saw you had already tested it that way. It correctly decoded it in about 10 minutes. Well done, very cool project!
Heh, alongside the documented trials, I’ve been giving other models the raw message and asking them to approach it as an unfamiliar recipient, with zero hints. I’ve had successful decodes that way too. Of course, LLMs know a great deal about chess, but still it’s encouraging to see it work
wow!
https://en.wikipedia.org/wiki/Wow!_signal
[flagged]