This is a small, curious little program with its own eyes, ears, hand, and
voice. Watch it teach itself the alphabet, then show it a letter and it will say the sound and draw the
shape. You can teach it your own voice, hide letters in a word and watch it work them out, and even switch
to a bigger set of "receptors" to see it draw crisper. Everything happens in your browser.
Careful with the words. This is a tiny simulation, not a real child. It does
not see, hear, understand, or read the way we do — it just spots which shapes and sounds keep showing
up together and counts. The sounds are a little body ringing like a bell, not a voice. Nothing about
you is uploaded or saved.
What to do:① wait for it to teach itself the alphabet (a few seconds) ·
② press a letter and it will say and draw it ·
③ try teaching it your voice or a bigger receptor grid
· the little green badge tells you the browser and the reference program agree, receptor-for-receptor.
idle — press Teach
① Teach the being
watch it teach itself — the little dials spin as it works, and it stops when there's nothing new to learn
② Show it a letter → it says & draws
press a letter — it will say the sound with its own little voice and draw the shape with its own little hand
How sharp are its eyes? Give it a bigger eye and teach it again:
A bigger eye means more little dots to see the letter with — and a matching hand that can draw with more little dots. Its "IT MAKES" picture gets less blocky and its memory of each letter gets finer. Switching restarts its learning (voice recordings and word memory reset). The little green badge always refers to the starting 8×8 being — that's the one we can check against the reference program.
shown→
·
read-out→it draws
③ Play it a sound → it draws the picture
press a sound — it listens, and then inks the letter it thinks it heard, from memory
🔊
heard→it makes
④ Teach it your voice → watch it learn in real time
hold a letter button and say it out loud; its little ear listens and remembers — no waiting, no training run, just counting
This being has never heard a human voice. Its ear is 64 tiny "strings" tuned across the range your voice lives in — so any sound you make lands on those strings and becomes something it can learn from. Microphone audio is just a demo — nothing is uploaded or saved. The built-in "teacher" tones are just bells ringing (not real speech), which is why they sound rough. Your voice replaces them.
press & hold a letter and say it out loud (a few times each):
press & hold each letter a few times, then hold & guess
was it right?
Each recording is assimilated live (running-mean prototype + counts) and bound to the letter's cause — the audio dictionary grows and recognition climbs as you teach more. Real online learning, no re-training. Keep your takes of a letter consistent; wildly different ones just spawn extra prototypes (still bound to the same cause).
⑤ Read a word in context
hide a letter in a word — it uses the letters it CAN see to work out the missing one, the way you finish a smudged word on a page
word · hide position
The being sees only the other letters, infers the word, and
imagines the hidden one from the word posterior — then we occlude that letter 85% and show that
context recovers it where the eye alone fails. "Cloze", never "comprehension".
⑥ Forgiveness — letting a stuck idea change
क्षमा — when it clings to the wrong answer, "forgiving" it doesn't erase what it learned; it just softens its grip so new evidence can move it. The table shows how many correct examples are needed with vs. without forgiveness.
Overturning a belief built from R wrong observations needs ~R correct
ones; forgive(f) cuts that to ~f·R — measured, monotone. The owner's
subtle-system spec, as tested count math (never therapy language).
An honest negative
recorded as prominently as the passes
UNI·Sensorium v1 · in-browser port ≡ Python reference (parity above) ·
no LLM, no backprop, no clock · real audio/graphics are non-citable demos.