Vertexpace / Light Code / NovaGlyph

Universal Code Map

How AI evolved from rigid if/then rules to adaptive learning — and how Light Code bridges the gap

1950s
Symbolic AI
Hand-coded if/then rules. Symbols manipulated by logic.
Logic Theorist
ELIZA
Shakey
1970s–80s
Expert Systems
Thousands of domain rules from human experts. Brittle to new cases.
DENDRAL
MYCIN
Prolog
1990s–2000s
Machine Learning
Learn patterns from data. Rules discovered, not written.
SVMs
Random Forests
Naive Bayes
2010s
Deep Learning
Neural nets with millions of parameters. Opaque but powerful.
AlexNet
GPT
Transformers
2026
Light Code Planes
75-concept universal layer. Rules + learning + adaptation on 64 bytes.
PREDICT
DECIDE
LEARN
02 — The Core Problem & The Fix
Why GOFAI Failed
🔒
Static rules Every behaviour hand-written. No pathway to update itself.
🧱
Brittle edges Anything outside the rule list — blank. ELIZA can't handle a new word.
📈
Rules only grow MYCIN had 600 rules. More complexity = more rules. Never shrinks.
🚫
No feedback loop ELIZA doesn't know which responses worked. It can't improve.
🗣️
Expert bottleneck Every rule needs a human to write it. Doesn't scale.
How Light Code Fixes It
🔄
64 bytes, reused POLYGRID constraint: planes reuse the same 64 bytes. Meaning shifts, not size.
🧠
Semantic primitives 75 concepts are universal meanings, not arbitrary strings. Distance is computable.
⚖️
Weighted tendencies Rules become weights on concepts. LEARN adjusts them from outcomes.
🔁
Closed loop PREDICT → DECIDE → CREATE → LEARN → back. Every cycle sharpens the next.
🤖
Self-modifying agents Faulted agents are rewritten by LLM and respawned. System heals itself.
75
Universal Concepts
64
Bytes per POLYGRID plane
Core / Control
Flow control
Memory / Register
I/O
Registers
Float / Crypto
0
backup
1
read
2
write
3
link
4
receive
5
delete
6
create
7
update
8
run
9
stop
10
urgent
11
now
12
soon
13
later
14
start
15
end
16
open
17
close
18
medium
19
immediate
20
file
21
process
22
memory
23
network
24
disk
25
kernel
26
user
27
system
28
local
29
global
30
alive
31
dead
32
idle
33
busy
34
ready
35
waiting
36
running
37
load
38
save
39
reset
40
to
41
from
42
send
43
find
44
get
45
put
46
push
47
pull
48
call
49
return
50
connect
51
split
52
merge
53
filter
54
sort
55
map
56
reduce
57
expand
58
compress
59
encode
60
decode
61
secure
62
channel
63
swarm
64
sync
65
flash
66
pulse
67
echo
68
lock
69
free
70
trust
71
init
72
clone
73
kill
74
heal

Each concept is simultaneously an opcode (in LuminaVM), a semantic tag (in agent memory), and a vocabulary token (in NovaGlyph). Same word, three uses.

POLYGRID constraint: all four planes operate on the same 64 bytes. The meaning of each byte changes per plane. This is how you get adaptation without growing the codebase.

📥
Input
What happened?
Sensor data, user message,
agent IPC, OS event
🔮
Predict
What will happen?
Generates expectation.
Weights from past outcomes.
Confidence score output.
⚖️
Decide
What should I do?
7-step loop on 64 bytes.
Chooses action from
PREDICT confidence map.
Create
What do I make?
Generates response/action.
Recursive slot machines.
Personalised from memory.
📤
Output
What was sent?
Response delivered.
Outcome observed.
Logged for LEARN.
LEARN plane Reads logs from all three planes → computes delta → updates weights in concept memory → feeds improved weights back to PREDICT
PREDICT
Status: Shipping ✓
DECIDE
Status: Shipping ✓
CREATE
Status: In development
LEARN
Status: Shipping ✓
GOFAI — ELIZA (static rule) if keyword == "mother":
  reply = "Tell me about your mother"
elif keyword == "father":
  reply = "Tell me about your father"

// Can NEVER update itself.
// Same response in 1966 as in 2066.
// Unknown word = no match = silence.
Light Code — weighted concept memory // weights stored in agent memory
memory write weight_memory 180
memory write weight_process 120
memory write weight_stop 200

// LEARN plane adjusts after each cycle:
if outcome == good:
  weight_memory += delta // reinforce
else:
  weight_memory -= delta // weaken
Concept weight distribution after 100 LEARN cycles (example)
stop
200
+12 ↑
memory
180
+8 ↑
process
120
−4 ↓
idle
60
−15 ↓
run
155
+22 ↑

These weights live in agent memory as concept-tagged keys. Every agent carries its own learned weights. Agents with different histories behave differently — even running the same Light Code.

🧠

Predictive Coding (Brain)

The brain constantly predicts what it will sense next. When reality differs from prediction, it sends an error signal upward to update the model. Perception is literally a controlled hallucination that gets corrected by reality.

Neuroscience Karl Friston
🔮

PREDICT Plane (Light)

PREDICT generates an expectation from current concept weights. When CREATE's output is compared to the real outcome in LEARN, the delta is the "prediction error." LEARN propagates this back to PREDICT's weight table.

Light Code POLYGRID

Why It Beats Deep Learning

Neural nets need millions of examples and GPU clusters to update. Light Code's 75-concept weight table updates from a single outcome — because the concepts are already semantically meaningful. Less data, faster adaptation, fully on-device.

On-device Few-shot
External World
Lumina OS Kernel
75-Concept VM (LuminaVM)
PREDICT plane
DECIDE plane
CREATE plane
LEARN plane
Semantic Memory
Concept-tagged keys
Genesis Grid (distance)
Rubik's Crypto
+
Luminous Codec
+
IPC Bus
Agent Mesh
LightNet (P2P)
LUMINA Phone (Swift)
LUMINA STONE (ESP32)
Pi bare-metal
All compute: concept words · All storage: concept-tagged memory · All transport: Luminous-compressed · All crypto: Argon2id+AES-256-GCM
Property GOFAI Deep Learning Light Code Planes
Rules Hand-written Learned (opaque) Weighted concepts (transparent)
Adaptation None Requires retraining Each cycle (online)
Data needed Expert knowledge Millions of examples Single outcome
Explainability Full (read the rules) Black box Full (read weights + concepts)
Compute Tiny GPU cluster On-device (ESP32 / Pi)
Unknown inputs Silence / crash Generalises (imperfectly) Nearest concept distance
Memory grows? Yes (more rules) Yes (more params) No — 64 bytes, reused

Good question — they are the same structure. That's the point.

Both systems match a pattern to produce a response. Light Code didn't invent a new kind of thinking. It added one line at the end that GOFAI never had.

ELIZA — 3 steps, last one missing ① MATCH if keyword == "mother"

② RESPOND   reply = "Tell me about your mother"

③ UPDATE — does not exist   (nothing happens)

// Runs identically in 1966 and 2066.
Light Code — same 3 steps, ③ now exists ① MATCH if concept == memory AND weight > threshold

② RESPOND   take action

③ UPDATE ← the only new step   if outcome == good:
    weight_memory += delta
  else:
    weight_memory -= delta
ELIZA execution loop
match → respond
match → respond
match → respond
← same forever. no state changes.
Light Code execution loop
match → respond → update weight
weights shifted
match → respond → update weight
weights shifted again
match → respond → update weight
← same input now matches differently. history matters.
The concrete parallel — word for word
Step ELIZA Light Code
① The pattern keyword == "mother" concept == memory
② The response "Tell me about your mother" run the action
③ After response nothing weight_memory += delta
Next time it runs identical slightly different
The Honest Summary
Light Code is GOFAI.
GOFAI's problem was never the if/then. The problem was that each rule had no confidence score and no mechanism to update. Light Code keeps the if/then — it's cheap, explainable, runs on an ESP32 — and adds the one missing piece: a weight per concept that the LEARN plane adjusts from outcomes. That's it. No neural net. No matrix multiplication. GOFAI + weights + one update step per cycle.