COGG9 No-Ocosm
A continuing world for AI research.
Executable participants encounter a persistent world, preserve information, develop capabilities and can contribute them back to the whole system. The research system remains private; public availability will be announced separately.
The active-inquiry mechanism worked in bounded controlled cases. A prior confirmatory experiment did not establish a reliable advantage over matched fixed search. Both results are part of the story.
- Persistent World
- Material Memory
- Active Inquiry
- Public Interface Planned
Four main lanes, with new research questions opening beside them.
COGG9 is the public layer around the AI research and development I’m doing. Not a finished platform. Not a pitch deck. It is a working notebook with the labels left on.
The work is split because each piece needs its own lane. COGG9 Agent deals with memory, tools, recovery, and project state. COGG9 asks what kind of model/core could grow inside that environment. WaveCodecLLM asks how meaning might move through the system without wasting so much compute. BHVC asks whether model weights can store reusable structure once instead of paying the full storage cost again for every tensor.
The projects have different jobs. COGG9 Agent is the workspace; COGG9 is the custom model research. HASHNODE-256 is a separate native AI research direction that grew out of a hardware experiment. WaveCodecLLM and BHVC remain separate signal and storage questions, while Node Multiplexing is a governed project inside the model/core lane. Sharing a motivation does not make these a working integrated system.
A body, a growing core, a signal lane, and a storage question.
That is the plain version. Each project card below opens a deeper page. I want the homepage to be the front door, not the whole explanation crammed into one scroll.
COGG9 Agent
The harness around long AI work.
COGG9 Agent is the self-hosted AI workspace I’m building for long-running work: project-owned memory, visible initiative, governed tools, reviewable outputs, and recovery when things break.
The model can change. The project, the work, and the relationship should not have to disappear.
- AI Harness
- Project Memory
- Tool Use
- Recovery
COGG9
The model/core I’m trying to design for that body.
COGG9, formerly PlasticNodeLM, is the experimental model/core direction I’m building around growth, structure, continuity, memory-aware design, and local hardware.
COGG9 Agent is the environment and harness. COGG9 is the separate model/core direction; this rename does not create an integration decision.
- AI Model
- Model Growth
- Continuity
- Local Hardware
HASHNODE-256
The hardware question became a model question.
HASHNODE-256 now investigates bounded language behavior, temporary context and selective lasting memory. The latest comparison did not show an advantage from expanding the hash-state field. The research has moved; the claims have to move with it.
Bounded experiments. Simpler comparisons. Negative results kept in view.
- Language Research
- Temporary Context
- Selective Memory
- Bounded Evidence
COGG9 Node Multiplexing
One physical node. Many logical possibilities.
Can shared physical neural capacity support multiple useful logical nodes? This project explores specialized internal programs, private states, concurrent streams, and developmental headroom.
The early evidence is controlled and synthetic. The larger mechanism remains unproven—that is what the next experiments are for.
- Logical Nodes
- Shared Capacity
- Private State
- Governed Testing
The signal lane: less waste inside the machine.
WaveCodecLLM is my compression and machine-meaning research. Human words matter at the edge, where people guide and review the work. Inside the machine, I’m asking whether meaning can travel in a tighter form without disappearing into a black box.
The goal is not “make it smaller” for its own sake. The goal is to keep what matters and stop dragging the whole closet through every internal step.
- Compression
- Machine Meaning
- Signal Paths
- Diagnostics
Blackhole Vector Compression
Can model weights share one compact structure?
BHVC is active compression research for AI weights. The current target is to approach Q8-class storage while reconstructing exact BF16 or FP16 weights and keeping behavior near the FP32 reference.
The early evidence is synthetic, measured, and honest: shared-state reuse crossed over against scalar int16 across multiple batches. Real-model tests come next.
- Shared State
- Exact 16-bit
- Byte Accounting
- Negative Results
COGG9 research notebook
A home for AI work that remembers.
I kept running into the same problem. A chat would help for an hour, then the work would scatter: one decision in a transcript, one note in a folder, one half-finished test in another place. The machine was useful in the moment, but the project still had no body.
COGG9 is where I’m documenting the attempt to fix that. COGG9 Agent is the harness around the work. COGG9 is the model/core direction. WaveCodecLLM is the signal lane. BHVC is the storage-compression research lane.
It is early, messy in places, and still changing. That is why I’m showing it while it forms.
What moved. What still has to hold up.
Native desktop progress. A changing model question. And a result where more hashes did not mean better cognition. I have refreshed all three project pages to separate what happened from what I still want to build.
The same question keeps showing up: can AI work keep its shape over time?
Memory, model structure, signal paths, and local hardware pressure all pull on the same problem. If the system cannot remember, organize itself, communicate efficiently, and run close enough to inspect, it is not the kind of machine I’m trying to build.
The world is part of the brain
COGG9 No-Ocosm tests whether participants, material memory, inquiry and accumulated capability can change a larger developing system.
Open No-Ocosm → HarnessA place for the work
Project context, tool use, memory, and recovery should not vanish every time a chat ends.
Open COGG9 Agent → ModelA core that can change
COGG9 asks whether a model can develop useful structure over time instead of staying frozen.
Open COGG9 → Native AI researchFollow the changing question
HASHNODE-256 investigates language and selective memory, while testing unusual ideas against simpler alternatives.
Open HASHNODE-256 → Logical nodesMore roles inside one structure
Node Multiplexing tests whether shared physical neural capacity can express several useful logical identities.
Open Node Multiplexing → SignalsLess waste inside
WaveCodecLLM asks whether machines can carry meaning more efficiently while people still get inspectable results.
Open WaveCodecLLM → StorageShared structure
BHVC tests whether exact 16-bit weight representations can reuse shared compression structure.
Open BHVC → HardwareNormal machines matter
The work keeps pressure from local hardware in view. If it only works in fantasy compute, it is not grounded enough.
Open system notes →The work is happening on a real local machine, not magic cloud compute.
The current COGG9 test box is an Ubuntu workstation with a Ryzen 9 CPU, 64 GB system memory, and two Intel Arc Pro B70 GPUs with about 30 GB of VRAM each. It is the machine I use to keep local hardware pressure in view.
I want the work to stay close enough to inspect.
Normal hardware creates pressure. Memory, compute, recovery, and tool use all look different when you cannot pretend the machine is infinite.
- Own the data and workflow
- Keep local hardware pressure visible
- Use tools with review points
- Show the research without exposing the blueprint
Follow the build while it is still forming.
The Patreon is for people who want the research notes, build notes, dead ends, and plain-English updates as the work matures. No finished platform pitch. Just careful work, shown honestly.
COGG9 is still being built in public.
For research questions, archive notes, or contact about the work: Edward Greenwood, cogg9research@gmail.com.