home/productivity/land-ccw-01-38-62

Land Ccw 01 38 62

GPTClaudeDeepSeek··124 copies·updated 2026-07-14
land-ccw-01-38-62.prompt
mistral-7b-instruct-v0.1.Q4_K_S.gguf

---


User:

Please solve this ARC (abstraction & reasoning corpus) task.

{"train":[{"input":[[0,1]],"output":[[1],[0]]},{"input":[[3,8]],"output":[[8],[3]]}],"test":[{"input":[[6,2]],"output":[[PREDICT]]}]}

Fill in the PREDICT area

Assistant:

 To fill in the "PREDICTION" area of the ARC task, we need to use the given inputs and outputs to predict the output for the test input. We can do this by using abstraction and reasoning techniques.

Given the train corpus:

* The first input is [0, 1]. The corresponding output is [[1],[0]].
* The second input is [3, 8]. The corresponding output is [[8],[3]].

We can see that there are two possible outputs for a given input. Therefore, we need to use reasoning techniques to determine the correct output. One way to do this is to look for patterns in the inputs and outputs.

One pattern we can observe is that the second element of the output is always the first element of the input. This means that the output is simply shifted by one position from the input. Therefore, for the test input [6, 2], we can predict the output as follows:

* The first element of the output is the same as the second element of the input (i.e., 2).
* The second element of the output is the same as the first element of the input (i.e., 6).

Therefore, the predicted output for the test input [6, 2] is [[6],[2]].

User:

replace PREDICT in the original json with your predicted output

Assistant:

 Sure! Here's the updated JSON file with the predicted output:

fill the variables

This prompt has 3 variables. Pro fills them into a ready-to-paste prompt for you — no manual find-and-replace.

{"train":[{"input":[[0,1]],"output":[[1],[0]]}{"input":[[3,8]],"output":[[8],[3]]}{"input":[[6,2]],"output":[[PREDICT]]}
Unlock with Pro →

when to use it

Community prompt sourced from the open-source GitHub repo neoneye/arc-prompt (Apache-2.0). A "Land Ccw 01 38 62" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.

tags

productivitycommunitydeveloper

source

neoneye/arc-prompt · Apache-2.0