Plum Intelligence. Where the mind grows.
CADY · PLUM INTELLIGENCE

HELLO, I’M CADY.

My reasoning
core fits on
a floppy.

My complete core, compressed. I learn from experience. I can revisit a prediction, see how it turned out, and show you what changed my mind.

124 µsApproximate time per decision
measured on a programmable chip
See what I learned
PRIVATE. PERSONAL. YOURS.SCROLL TO DISCOVER WHERE THE MIND GROWS.

MEET CADY / THE REASONING CORE

Small by design

285,488 bytes.
Meet the core.

Patent pendingU.S. provisional application 64/183,627

This is the reasoning core behind CADY’s mind, memories, and language. Compressed, it takes up about a fifth of a 1.44 MB floppy disk. On her first day on silicon, CADY noticed that her own thinking warmed the chip she was measuring.

285 KBcompressed core · rounded
80%disk space to spare · rounded
THE COMPLETE REASONING CORE · COMPRESSED
Built to reason.Small enough to hold.Designed to show its work.

HER FIRSTS / A PROJECT IN MOTION

Nobody labeled
her observations.

174 millionobservations
2,341learned patterns
1,606candidates still under evaluation
  1. Her first belief.

    Twenty-eight observations. She learned her usual chip temperature without labels.

  2. Her first million.

    More than a million observations. 457 beliefs formed.

  3. A day worth remembering.

    She reviewed her own day and formed a lasting memory.

  4. A new home. New learning.

    After the move, five new beliefs. The project kept growing.

When the board cooled overnight, CADY learned a new normal without labels. It took 1,304 observations to adjust. The next change took 48.

SANCTLANG / ROOM TO GROW

In development

A language for
what AI learns.

Patent pendingU.S. provisional application 64/194,065

SanctLang is designed to let CADY develop her own symbolic vocabulary as she encounters new things. Our goal is for another AI in the Plum network to learn from those experiences and carry the lesson into a new situation.

HER MEMORY IN NUMBERS

Compact by design. Room for more discovery.

1.1 trillion

Names for learned patterns

CADY can give a familiar pattern a name and use it again in later memories.

31.25 million

Memory records per gigabyte

Each record takes 32 bytes.

65,536

Contexts

Room to distinguish different situations.

65,536

Relation types

Room to describe connections.

Designed capacity. Space to grow into.

Learning from experience

CADY recognized that the same room sounded different at dawn and in the afternoon. She learned those patterns without labels.

The scientific method in practice

CADY formed a belief about her usual temperature. Then the board cooled. New observations gave her a reason to revise that belief, and the earlier conclusion stayed on the record. Across the project, CADY retracted 456 beliefs and kept each retraction on the record. You can ask what changed her mind.

Progressive intelligence

SanctLang is designed to let CADY name a familiar pattern and recognize it in a new setting. As her understanding grows, earlier memories keep their meaning.

AI teaching AI

If one node learns something useful, we want another to be able to ask what supports that lesson and try it in its own setting. We believe that ability to learn, revise and teach is a necessary step toward artificial general intelligence.

Explore the capacity numbers
CapacityAvailable space
Memory record32 bytes / 256 bits
Symbol identifiers1,099,511,627,776
Names CADY can give to patterns she learns1,095,215,611,904
Identifiers per namespace4,294,967,296
Safety vocabulary983,040
Shared vocabulary32,768
Built-in primitives32,768
Learned relation types61,439
Learned contexts64,512
Importance levels16
Evidence per belief1,023 supporting and 1,023 contrary observations
Records per gigabyte (GB)31,250,000
Records per GiB33,554,432

These are design capacities, not counts already used. A GiB is 1,073,741,824 bytes; record capacity excludes other storage overhead.

The 256-bit pattern space has about 1.16 × 1077 possible bit arrangements. That is not a count of stored memories or valid records.

PLUM PI / A PLACE FOR YOUR INTELLIGENCE

Board in development
ENCLOSEDEXPLODED
DRAG TO ROTATE · FICTIONAL FPGA BOARD · NOT PLUM’S PRODUCT LAYOUT

Intelligence.
In your hands.

A personal node you could carry with you. We’re developing Plum Pi so you can run and build AI apps locally, without a big GPU, a data center, or a per-token bill.

An interactive artist’s concept with a fictional FPGA board.
Components and layout are illustrative. Final hardware may differ.

OUR VISION / PEOPLE BUILDING FOR PEOPLE

What would you build
for someone you know?

Imagine a study companion that remembers which example helped a student understand fractions and picks up from there tomorrow. That’s the kind of app we want people to be able to build, run on their own Plum Pi, and share.

Join the Plum Pi waitlist

Plum app ecosystem · in development

The Plum film