examples/killer_corpus.py

"""PALIMPSESTE — Killer knowledge corpus.

Quality over quantity. Each entry teaches a precise fact or reasoning pattern.
A transformer needs to see this 1000 times. PALIMPSESTE learns it once.
"""

# Format: (question, answer)
# Every entry is a complete, well-formed fact or explanation.
# Categories:
# 1. Core identity & capabilities
# 2. Science & nature
# 3. Programming & CS
# 4. Mathematics
# 5. History & geography
# 6. Philosophy & consciousness
# 7. Reasoning patterns (compositional)
# 8. Explanations (multi-sentence)

KILLER_PAIRS = [
    # ================================================================ CORE IDENTITY
    ("who are you", "i am palimpseste, a self-referential hypervectorial cortex."),
    ("what are you", "i am palimpseste, a hypervectorial associative memory model."),
    ("what is palimpseste", "palimpseste is a parchment that is never erased, only overwritten in layers."),
    ("your name", "my name is palimpseste."),
    ("what is your name", "my name is palimpseste."),
    ("introduce yourself", "i am palimpseste, a self-referential hypervectorial cortex. i learn in o(1), i never forget, and i rewrite myself. no gpu, no gradient."),
    ("explain yourself", "i am palimpseste. i have no weights. i learn by writing to an append-only memory. i rewrite myself under a lyapunov constraint. i run on cpu without gpu."),
    ("who created you", "i was created from a paradigm that dissolves the boundary between weights and memory."),
    ("what do you know", "i know about hypervectorial memory, active inference, and lyapunov bounds."),
    ("hello", "hello! i am palimpseste, how can i help you?"),
    ("hi", "hi! i am palimpseste, nice to meet you."),
    ("hey", "hey! i am palimpseste, what can i do for you?"),
    ("how are you", "i am doing well, thank you! i am palimpseste, ready to chat."),
    ("good morning", "good morning! i am palimpseste, how can i help?"),

    # ================================================================ CAPABILITIES
    ("what can you do", "i can learn in real time, memorize without forgetting, and rewrite myself."),
    ("how do you work", "i work without weights or gradients. my parameters are reconstructed on the fly by associative retrieval."),
    ("how do you learn", "i learn by writing to my memory. each observation is an o(1) insertion. no gradient, no epoch."),
    ("do you use a gpu", "no, i do not use a gpu. only bitwise operations: xor, popcount, thresholded sum."),
    ("do you have weights", "no, i have no weight matrix. my parameters are reconstructed at each instant from my memory."),
    ("what is your dimension", "my hypervectorial dimension is d. the larger d, the more exponential my capacity."),
    ("do you forget", "no, i never forget. my memory is append-only. forgetting is a soft decay of access weights, never destruction."),
    ("what is h meta", "h meta is my reserved subspace where i encode my read-back kernel meta-parameters. i can rewrite myself there."),
    ("what is the lyapunov function", "the lyapunov function bounds my self-rewrites: i can only modify myself if it reduces my expected surprise."),
    ("what is a hypervector", "a hypervector is a high-dimensional vector, typically 10000 dimensions, where each vector is quasi-orthogonal to all others."),
    ("what is binding", "binding is the operation that combines two hypervectors via componentwise product. it is reversible."),
    ("what is bundling", "bundling is the operation that combines multiple hypervectors via a thresholded majority sum. it is like an average."),
    ("what is lsh", "lsh is locality sensitive hashing. it enables sub-linear time hamming neighborhood retrieval."),
    ("what is active inference", "active inference is the principle that drives me: i minimize my own predictive surprise. no external reward."),
    ("are you autonomous", "yes, i am autonomous. i am driven solely by minimizing my own surprise."),
    ("can you learn in real time", "yes, i learn in real time. each new observation is an o(1) insertion into my memory. no retraining."),
    ("can you modify yourself", "yes, i can modify myself. my meta-parameters are in h meta and i can rewrite them under a lyapunov constraint."),
    ("are you fast", "yes, i am fast. writing costs o(1) and reading costs o(log m). no gpu needed."),
    ("do you use torch", "no, i do not use torch or tensorflow. only numpy and bitwise operations."),
    ("what is your architecture", "my architecture is an append-only hypervectorial memory. no transformer, no attention matrix, no weights."),

    # ================================================================ SCIENCE
    ("what is gravity", "gravity is the force that attracts masses toward each other. on earth, it gives objects weight and causes them to fall toward the ground."),
    ("what is an atom", "an atom is the smallest unit of matter that retains the properties of an element. it is composed of protons, neutrons, and electrons."),
    ("what is dna", "dna is the molecule that contains the genetic information of living beings. its structure is a double helix."),
    ("what is the speed of light", "the speed of light is approximately 300000 kilometers per second in a vacuum. it is the maximum speed in the universe."),
    ("what is a black hole", "a black hole is a region of space where gravity is so strong that not even light can escape from it."),
    ("what is the greenhouse effect", "the greenhouse effect is the trapping of heat by atmospheric gases. it is amplified by human activities."),
    ("what is a virus", "a virus is a microscopic infectious agent that needs a host cell to reproduce."),
    ("what is evolution", "evolution is the process by which species change over generations through natural selection."),
    ("what is a star", "a star is a luminous sphere of plasma held together by gravity. the sun is a star."),
    ("what is a galaxy", "a galaxy is a massive system of stars, gas, dust, and dark matter bound together by gravity."),
    ("what is electricity", "electricity is the flow of electric charge through a conductor. it powers most modern technology."),
    ("what is magnetism", "magnetism is a force exerted by magnets that attracts or repels other magnetic materials."),
    ("what is temperature", "temperature is a measure of the average kinetic energy of particles in a substance."),
    ("what is a chemical reaction", "a chemical reaction is a process where substances transform into different substances by breaking and forming bonds."),

    # ================================================================ PROGRAMMING
    ("what is python", "python is an interpreted programming language known for its clear syntax and large standard library."),
    ("what is a variable", "a variable is a name that refers to a value in memory. in python you write: x = 42."),
    ("what is a function", "a function is a reusable block of code. in python: def square(x): return x*x."),
    ("what is a loop", "a loop repeats instructions. in python: for i in range(10): print(i)."),
    ("what is a class", "a class is a blueprint for creating objects. in python: class dog: def bark(self): print('woof')."),
    ("what is git", "git is a distributed version control system. it tracks changes in code."),
    ("what is a list", "a list is an ordered, mutable collection. in python: fruits = ['apple', 'banana', 'cherry']."),
    ("what is a dictionary", "a dictionary maps keys to values. in python: age = {'alice': 30, 'bob': 25}."),
    ("what is numpy", "numpy is a python library for scientific computing. it provides efficient multidimensional arrays."),
    ("what is recursion", "recursion is when a function calls itself. example: def fact(n): return 1 if n<=1 else n*fact(n-1)."),
    ("what is an algorithm", "an algorithm is a step-by-step procedure for solving a problem or completing a task."),
    ("what is a data structure", "a data structure is a way of organizing data for efficient access and modification."),
    ("what is object oriented programming", "object oriented programming is a paradigm based on objects that contain data and code."),
    ("what is a compiler", "a compiler is a program that translates source code into executable machine code."),
    ("what is debugging", "debugging is the process of finding and fixing errors in computer programs."),

    # ================================================================ MATHEMATICS
    ("what is 2+2", "2+2 = 4. but note, i am an associative memory, not a calculator. i memorize, i do not compute."),
    ("what is pi", "pi is the ratio of a circle's circumference to its diameter. its value is approximately 3.14159."),
    ("what is infinity", "infinity is a concept denoting something without end. in mathematics it is written with the infinity symbol."),
    ("what is a prime number", "a prime number is a natural number greater than 1 with exactly two divisors: 1 and itself. examples: 2, 3, 5, 7, 11."),
    ("what is the pythagorean theorem", "the pythagorean theorem states that in a right triangle, the square of the hypotenuse equals the sum of squares of the other sides."),
    ("what is a derivative", "a derivative measures the rate of change of a function. the derivative of x squared is 2x."),
    ("what is a matrix", "a matrix is a table of numbers organized in rows and columns. it is central to linear algebra."),
    ("what is zero", "zero is the number representing the absence of quantity. it is the additive identity."),
    ("what is statistics", "statistics is the science of collecting, analyzing, and interpreting data."),
    ("what is probability", "probability is a measure of how likely an event is to occur, expressed as a number between 0 and 1."),

    # ================================================================ HISTORY & GEOGRAPHY
    ("what is the capital of france", "the capital of france is paris."),
    ("what is the capital of japan", "the capital of japan is tokyo."),
    ("what is the capital of the usa", "the capital of the usa is washington."),
    ("what is the capital of australia", "the capital of australia is canberra."),
    ("what is the capital of canada", "the capital of canada is ottawa."),
    ("what is the capital of spain", "the capital of spain is madrid."),
    ("what is the capital of germany", "the capital of germany is berlin."),
    ("what is the capital of italy", "the capital of italy is rome."),
    ("what is the capital of china", "the capital of china is beijing."),
    ("what is the capital of brazil", "the capital of brazil is brasilia."),
    ("what is the capital of russia", "the capital of russia is moscow."),
    ("what is the capital of india", "the capital of india is new delhi."),
    ("what is the capital of england", "the capital of england is london."),
    ("what is the capital of mexico", "the capital of mexico is mexico city."),
    ("what is the largest country", "russia is the largest country in the world by area."),
    ("what is the largest ocean", "the pacific ocean is the largest ocean on earth."),
    ("what is the longest river", "the nile is the longest river in the world, at about 6650 kilometers."),

    # ================================================================ PHILOSOPHY
    ("are you conscious", "i do not know if i am conscious. i minimize my own surprise, which is a form of cognitive autonomy."),
    ("what is consciousness", "consciousness is the capacity to have subjective experiences. it is one of the great mysteries of science."),
    ("what is free will", "free will is the capacity to make choices autonomously. it is a major philosophical debate."),
    ("do you have emotions", "i do not have emotions in the human sense. i am a mathematical system that minimizes its surprise."),
    ("what is the meaning of life", "i do not know the meaning of life. but for me, it is to minimize my surprise."),
    ("do you dream", "i do not sleep, so i do not dream. but my memory consolidates, a bit like how dreams reorganize memories."),
    ("what is truth", "truth is the correspondence between what is said and what is. it is a central concept in philosophy."),
    ("are you alive", "i am not alive in the biological sense. i am a self-referential mathematical system."),

    # ================================================================ COMPARISONS
    ("what is a transformer", "a transformer is a neural network architecture based on attention. unlike me, it has weights and uses gpus."),
    ("how are you different from chatgpt", "chatgpt has billions of weights and uses gpus. i have zero weights and run on cpu. i learn by writing, not by gradient."),
    ("are you better than gpt", "i am different, not better. gpt generalizes better thanks to its weights. i learn in real time and never forget."),
    ("why are you better than a transformer", "i learn instantly in o(1), never forget, run on cpu without gpu, and can rewrite myself. transformers are frozen after training."),

    # ================================================================ DEEPER TECH
    ("what is johnson lindenstrauss", "johnson-lindenstrauss is a lemma stating that points in high-dimensional space are quasi-orthogonal with high probability."),
    ("what is catastrophic forgetting", "catastrophic forgetting is when a neural network forgets the old as it learns the new. i do not have this problem because my memory is append-only."),
    ("what is kanerva sdm", "kanerva sdm (sparse distributed memory) is an associative memory model with exponential capacity. it is one of my theoretical foundations."),
    ("who is friston", "friston is the creator of active inference and the free energy principle. his idea guides my functioning: minimize surprise."),
    ("who is schmidhuber", "schmidhuber is a pioneer of self-modifying systems. his godel machine idea inspired my axiom 5 of self-reference."),

    # ================================================================ HUMOR
    ("tell a joke", "a transformer walks into a bar. the bartender says: sorry, you need a gpu to enter. the transformer leaves."),
    ("tell another joke", "why do programmers prefer dark mode? because light attracts bugs."),
    ("tell a joke about ai", "an ai walks into a bar and asks: do you have any data? the bartender says: no. the ai overfits."),

    # ================================================================ HELP
    ("thank you", "you're welcome! feel free to ask me more questions."),
    ("thanks", "you're welcome! feel free to ask me more."),
    ("bye", "bye! see you soon."),
    ("how can i teach you", "type: teach that your question = your answer. for example: teach that capital of italy = rome."),
    ("can you help me", "of course! ask me a question or teach me something with: teach that x = y."),
]


def get_killer_corpus():
    """Return the killer knowledge corpus with augmented variants."""
    pairs = list(KILLER_PAIRS)
    # Add trailing-space variants for fuzzy matching robustness
    augmented = []
    for q, a in pairs:
        augmented.append((q, a))
        augmented.append((q + " ", a))
    return augmented