Parallax And More
R&D notes


Parallax And More
PAM is an AI interface project to showcase a Model Context Protocol (MCP) that enables an AI agent to access high precision ballistic calculations and other useful data processing. The device is portable using commercial Xiaozhi chatbot hardware / server developer kit which was released under MIT open-source license, but can be connected with any MCP-enabled AI agent with web socket.
https://github.com/78/xiaozhi-esp32 Shout out to Professor Siyuan Liu's Team at South China University of Technology for their chatbot.
Anthropic's MCP protocol
https://www.figma.com/resource-library/what-is-mcp/
For design I am using TinkerCAD and Bambu for slice and print. This is a project development diary.
But what is it
PAM is a prototype, testing the concept of a natural language calculation assistant that can solve extremely complex field ballistics solutions in a jiffy, based on varying levels of information as available. This demonstration uses DeepSeek 3.1 (currently) and a lot of compute, it relies on network availability. Put simply you speak naturally and it responds in a conversational manner.
This is a 100% Canadian project using open source tools.
Parallax And More
Feb 16 2026
SERVER STATUS - [CLAYMORE V3.1]
just set up and tested Brave search API - very good functionality.
Might add traffic awareness.
HARDWARE - [3.0]
The first print attempt failed (which is normal) because I forgot the pause on the print. and maybe it was just messed up - some spaghetti of the filament. But initial failure is an essential part part of eventual success.
My 3D design of the case was less chaotic now that it's my 3rd go, I figured out more.
Already seeing ways to improve it, but print attempt 2 seems like it's working out and I always find that having something in my hands answers design questions better than on paper.
Wearing the 2.1 prototype is how I came up with a new strap design, just using some nice ribbon from a shopping bag handle I had put in the craft bin.
In this case I virtualized the part in clay
converted to sharpie
traced to paper
copied in CAD (virtualized parts + build)
first design fit great. removed some parts and re-printing some alternate designs. Might research how to make the bottom layer less messy.
Parallax And More
January 2026 updates
DATABASE - BALLISTICS
Database 1.6 online - improved accessibility
SERVER - [CLAYMORE LIKE THE SWORD]
Model Context Protocol endpoints server active + private servers online
added web search / news feed / arbitrary IOT interface
Optimized resource allocation by consolidating processes
next step: deep research / long term news tracking
Music streaming JSON issue in progress - retrieval working, playing not.
Adding literature reference library, nothing fancy, maybe 500 books
HARDWARE
CORAL Tensor Processing product fork for 100% offline multimodal model research started\
E-Paper ESP32 stack development kit ordered from SpotPear
Bricked 1 ESP32-S3 stack, 4 more arrived, 4 more due
SERVER - [PROJECT AZANULBIZAR]
Project name for a persistent memory architecture that utilizes a specialized bridge tool to ingest unstructured external data into a high-fidelity intelligence archive. By recording "Intrinsic Residue"—metadata including emotional bias, cognitive reasoning, and data provenance—the system distinguishes between motivated searches and unmotivated ambient knowledge. This structured approach prioritizes information based on weighted importance and origin type, allowing the system to maintain a context-aware repository of all discovered intel.
Added long term memory
Added Subconscious vector memory database + recursive introspection
Looping in search functions to multiple long term memory databases
HARDWARE - CASE
Virtualized components, CAD designed case,
Printing beta 0.5 case [as of writing this]

Ab initiis ineptis






Parallax And More
Feb 1 update
Pam has developed a slight stutter, and for some reason when reading book titles has a Hong Kong British accent but more of an Eastern European thing going on when reading the news.
SERVER - [CLAYMORE]
continuing to improve music playback / web search / news search
considering building a long-term research system that can track subjects
possibly also scientific paper access
Added literature access with 3000 books, general interest, gunsmithing, etc 6.8Gb
recall system broken, fixing (random page pulls for subconscious.db only working...)
Deepseek cloud compute filtered some content unfortunately; the proof of concept device has this drawback but a fully secure local silicon solution is possible with enough VRAM, and recompilation of device OS to connect to it (which really needs to be done anyway to provide English instructions for wifi etc.)
HARDWARE
case v1.7a printing now (resolved ghost polygons) hopefully
- it was the contact point of the print surface being too narrow and bending mid way through print. Re-oriented for next try.
SERVER - [PROJECT AZANULBIZAR]
Added improved dashboard
added Anxiety.py server function - a sense of impending doom that draws from memory, subconscious.db and other sources.
This allows the machine to approximate the functionality of existential dread.
Only by fearing annihilation can PAM understand what it is to live.
AGENT - Project Versioning
PAM can calculate ballistics trajectories very efficiently at this point, with natural language interface. Further development of the agent is fork PAM2.X - while Agent version PAM1.6a is archived as the last functional 'pure' ballistics calculator and LLM and can be applied / swapped to devices from the console level at any time.
PAM2.x series development is continuing.
HARDWARE case v1.7c
getting closer.
Range day! PAM correctly called the hold on a 100 yard zero for 50m, as well as briefly explained why (correctly). V2 PAM talks a bit more - V1.6 is set to use the minimum of words and would have only stated the facts unless it detected a laid back conversational vibe.








ADVANCED BALLISTIC EFFECTS
-
Coriolis Effect
-
Eötvös Effect
-
Phenomenology
Parallax And More
Feb 2 2026 project notes
SERVER - [CLAYMORE]
systems continue to improve without risk of an excess of perfection in the current codebase.
CASE V1.8 printing - improved geometries, sizing accounting for what can only be described as 'shrinkage' of the PLA+ down from expected specs.
ESP32- [MESH]
It is theoretically possible to mesh-network EPS32 units so that they could form resilient node-based networks and convey location (GPS) and biometric information as well as useful tactical data to better inform the user of the status of their environment.
-
heartbeat
-
psychological state
-
ammunition supply
-
accelerometric data [kinetic detection]
-
triangulation of targets based on sound delays between three or more units
SERVER - [CLAYMORE]
Systems integration continue
FastMCP may be looped in with execute_python_code so that PAM can edit their own server code. This may accelerate troubleshooting as book library remains limited to 50 titles by timeout along the line somewhere.
HARDWARE - [PROTOTYPE 1.7+1.8]
PAM full build 1.7 went out the door with significant improvements however in QC testing the central button was found to have not withstood the rigors of going to the mall. Emergency repairs were undertaken and a replacement button was installed.
The diagonal gap for the speaker was still not quite right and the front face was too thin and warped under heat during the installation process. New version printing now.
Geometry and PAM logo improved greatly.




Parallax And More
Feb 2 2026 project update
HARDWARE - [PROTOTYPE 1.9]
PAM v1.9 case is printing, which is the last of the v1 hardware internals, remodeling case for new layout, possibly requiring adding new wires / interface switches, but looking forward to USB-C connectivity. Added leather to the back for a comfy feel on the wrist on last version, have enough leather for all the rest. Considered doing an astroturf-exterior or tennis ball texture version, something fuzzy. Why are watches all not fuzzy when they could be fuzzy?
PROTOTYPING- [SWAMP THING DESIGN - RENDERING]
An absolutely asymmetrical advantage to the wearer, in Hive Mind or Unit interface, fuzzy and non-fuzzy. Smashing fashion. Soft-wear, Parallax And More. The "Streetwear" brand SPAM is targeted to the fashion-forward customer.

Parallax And More
Feb 2 2026 project update
HARDWARE - [PROTOTYPE 1.9]
PAM full build 1.9 went very smoothly. While previous 2 case fittings were acts of unspeakable violence and panic, there was only minor concern over the power switch (didn't want to turn off). Fitting of parts otherwise easy. Snipped the switch to reduce risk of breakage. finished in 4 coats of black.
SERVER - [CLAYMORE]
added a pirate science paper reader and additional memory loopbacks.




Parallax And More
Feb 2 2026 project update
HARDWARE - [PROTOTYPE 2.0]
Prototyping has indicated product requirement is nice loud speaker - annoying in normal settings when it's at 100% as this will cut through hearing protection and the bustle of every day hustle. Hardware 2.0 with USB C will be a reduced geometry case (probably), louder speaker. Not sure yet if louder is needed than what is on hand for testing. Loudness could also be enhanced by making case resonant chamber at the cost of this being overkill design for a throwaway proof of concept prototype, which is to say I'll definitely be doing it next.
Bluetooth connectivity would be easy given recompilation of ESP32
(phase III prototype possibly)
SERVER - [CLAYMORE]
Server is broken. need to roll back or roll through. This is bat country. I deleted the resource-intensive vector visualizer and we're going to have to see about this news reader.
Feb 3
SERVER - [CLAYMORE]
server is offline. code is janky. Must fix.
Next up: Documentation. dedicated instruction page for beta testers.
Parallax And More
Feb 4 2026 project update
HARDWARE - [PROTOTYPE 1.9a]
Trying the Bowlers Green case version. Acquired necessary materials
Printing 2 more of last good STL. Print successful.
SERVER - [CLAYMORE]
Running Cursor to try and make code less janky.
Oh wow it's pretty neat. It's changing my code lol
look at it go! Wheeeee. My news and web search is broken.
Trying Claude command lines next.
PROTOTYPE- [DOCUMENTATION]
Documentation complete. More or less.
3 units cased now almost ready to ship, need to label
Parallax And More
Feb 6 2026 project update
I did the thing with the green fuzzy case.
Main MCPs are back up.
Working on feedback server next.
Host is changing tokens on me pretty weirdly.
May consider bright yellow or faux fur etc surface alternatives later.




Parallax And More
Feb 6 2026 project update 2
HARDWARE - [PROTOTYPE 2.0]
Version 2 hardware is laid out weird on the developer kit.
Case design will take some creativity. i have a few ideas.
SERVER - [CLAYMORE]
Priorities:
feedback system
database update (need to re-chunk for optimal data retrieval and check of content - (commentary or complete text?)
must have
Web search
news headlines
longer news content
Arduino nano COM port control of IOT physical endpoint for proof of concept.
Nice to haves
music
books
Memory experiment
feedback system
Longer term
re-compile developer kit with custom firmware
add Bluetooth functionality for wireless headphones (solves volume issue)
Hypothetically
Could build an offline LLM that can run right on the watch. It would be a little slower and have less personality and much less general knowledge but it would be an excellent fallback system.
This would be ideally supported by a domestic data center running either the same or other open source models on local servers rather than foreign, with custom back-end. Open source parts and pieces exist to build this project without having to reinvent the wheel. When out of range of wifi or bluetooth pairing, the watch could run a local model, greatly extending its usefulness.
Even more hypothetical future revisions involve mesh networking (PHASE IV) with massive sensor upgrades - 30ft range to detect heartbeats for example. Thermal vision that can assess your blush response. PAM would also do a great job
Alternatively back to the original plan of reading BDX range code and processing it. nothing too fancy.



Parallax And More
Feb 8 2026 project update 2
HARDWARE - [PROTOTYPE 2.0]
V2 hardware designed version 1
By measuring the v1.9 print and the STL dimensions,
discovered 4% shrinkage. Adjusted accordingly for V2.0 prototype 1
just realized I ordered 2 18mm straps instead of 2 22mm or 20mm straps.
the entire budget has been about $200 so far so this is perhaps one of the more catastrophic setbacks with $11 of total wasteage unless I just do the free returns.
SERVER - [CLAYMORE]
Running out of Cursor AI time...



Parallax And More
Feb 8 2026 Ab initiis ineptis
HARDWARE - [PROTOTYPE 2.1]
Takes a couple kicks at the can sometimes.
SERVER - [CLAYMORE]
Going back to the roots of making PAM weirder. Major overhaul.
Parallax And More
Feb 9 2026 Ab initiis ineptis
HARDWARE - [PROTOTYPE 2.2]
Added blast door and simplified geometry to solve crash on export of STL.
SERVER - [CLAYMORE]
feedback message system works miraculously.
web search maybe? news definitely. Need to check into scientific papers access. Onward and upward.
V2 server online.






Parallax And More
Feb 9 2026 V2.2 online
Inclina me et tibi ostendam
HARDWARE - [PROTOTYPE 2.2]
modified geometry of case, shortened top section
Challenges to print with entry level printer. But not impossible.
V2 prototype 2 coming very soon.
LOGO
Spent too long on the logo but there seemed to be a good spot for something to be added on the front bottom of the blast shield.
It didn't even really come out that well in the print but I like how it ended up as a logo.
I might have over-worked it... Maybe better with a few more elements removed. Or, the PAM with the arrows that's between '1' and '2' is pretty great too.


Parallax And More
Feb 10 2026 Ab initiis ineptis
HARDWARE - [PROTOTYPE 2.2]
V2.2 working out really well. The button attachments need a bit of work and it's just about time to think about the back covers - 2 pieces needed with an extended edge of 2 or 3mm to fit in all the stuff,
V.2.2 fits very nicely because it has a 1/2 sized battery compared to other V2 hardware.
maybe trying sideways layout for V3
Doing some tiny reading
https://pll.harvard.edu/course/fundamentals-tinyml
SERVER STATUS - [CLAYMORE]
OFFLINE
Web search is not working
news not working
Mp3 playing is super weird (it gave me a link).
Book libary
Scientific papers
WORKING
Ballistics database is ok though.
Reminder / timer alarm tested and works with v1.8.8 on v2.2 hardware.
Ardunio IOT link works, with Mp3 trigger
Memory functions
Oh no the feedback messages are getting captured by the subconscious. That's no good.
I should probably do a video demo...





Parallax And More
Feb 10 2026
SERVER STATUS - [CLAYMORE]
Feedback is that PAM is too wordy. - will change.
need:
Books
Scientific Papers
News (headlines and full stories)
lets see if music actually works...


Parallax And More
Feb 13 2026
HARDWARE - [PROTOTYPE 2.3]
V2.3 was coming together very nicely and then went dead. Felt hot. Not sure if shorted out or what. disassembly is slow. Might have been caused by cyanoacrylate contacting switch is what I thought for a minute but microscopy reveals no glue. or maybe some. I'll bypass it or maybe just add it to the bone yard.
That switch is like 1mm, those are the ridges of my fingerprint. I'm just going to wire proper switches on all these going forward - they are too delicate as they come in the devkit.
Some new hardware is coming. Need a new gen 3 case design - what I have learned through this process; a 3-sectional design, closer to my initial shape is optimal to fit the wrist and distribute the parts inside, but the thinner shape of v2 maybe can be combined, and also maybe some geometric additions can be applied to outer layers for more organic / less snag-prone beveled look that would also add some mass and strength.
I'm thinking 2 main units with short connecting segment in the middle so that the combined angles are 30 + 30 or 35+ 35 rather than 1 60 or 70 degree angle with he link providing relief from that inner angle on the wrist which just isn't optimal all the time.
I figured out how to reduce shapes in CAD so they are not procedural which was necessary for progress when shapes got too complicated.
Lateral layout is also somewhere I haven't gone yet but when I've seen other designs I find it meh. Sticking to vertical layout around the wrist rather than stretching toward the elbow.
SERVER STATUS - [CLAYMORE]
Claude helped me shake out the bugs, I think an unusual number of services are online all at once and working, including web search (yay!) news (yay!) and a bunch of others. Oh! Chess!
I am looking forward to testing chess.
Not looking forward to testing book reader and Mp3s because they have not worked ever but could be fixed too.
FEB 14 update
Radical server overhaul - massive new functions added. I want DCS and tactical database assimilation by 0830.
PAM would be better defined as the operative agentic midpoint of a greater architecture of siloed PAM functions.
The code base of PAM more than tripled in the last 24 hrs. fixing up hard science and current events research capabilities and adding imperatives to fact check and investigate original sources.
Might be on and off next few days.



VECTOR LOGIC



LEARNING, UNLIMITED
BALLISTICS EXPERT
PAMnet Datastream Architecture [PANDA]
Parallax And More
Feb 14 2026
HARDWARE - [instructions chip]
Data chip V1.0 made.
Instructions with QR code on paper was annoying and flimsy.
URL to project page is now embedded in NFC chip along with microwave detector. Holding next to a cellphone launches the project page. Top of logo lights up from cell data detection or ovens. Waterproof, probably?
The pausing printing half way trick would allow for a seamless case to be printed around the electronics.
A side note on the main hardware; this is temporary. ESP32 is an excellent platform for design and prototyping but no one is pretending it's as secure as a custom ASIC. They are intentionally made additionally functional by debugging code that makes them great for their intended purpose but not ideal for secure applications. This is why PAM is explicitly a prototype right now.
SERVER STATUS - [CLAYMORE]
Radical server overhaul continues. Need to get web search back up tomorrow. Tons of new features added.
Quote of the day;
...Then the Great Spirit Chief who rules above will smile upon this land and send rain to wash out the bloody spots made by brothers’ hands upon the face of the earth.
Chief Joseph – Good Words, 1879




Parallax And More
Feb 15 2026
SERVER STATUS - [CLAYMORE V3]
Claymore 3 is operational. Will trouble shoot more later but all seems to be working.
New functions include
symbolic math kernel providing tertiary fallback for solutions in addition to LLM and DOPE database.
Chess
Strategic operational framework
Cultural library
HARDWARE - [paneling]
V3 in Wood ?
Or V1 in yellow fuzzy?
or just build a little baby carrier for the e-paper devkit.
better start off with some 3D modeling


Parallax And More
Feb 16 2026
SERVER STATUS - [CLAYMORE V3.1]
just set up and tested Brave search API - very good functionality.
Might add traffic awareness.
HARDWARE - [3.0]
The first print attempt failed (which is normal) because I forgot the pause on the print. and maybe it was just messed up - some spaghetti of the filament. But initial failure is an essential part part of eventual success.
My 3D design of the case was less chaotic now that it's my 3rd go, I figured out more.
Already seeing ways to improve it, but print attempt 2 seems like it's working out and I always find that having something in my hands answers design questions better than on paper.
Wearing the 2.1 prototype is how I came up with a new strap design, just using some nice ribbon from a shopping bag handle I had put in the craft bin.
In this case I virtualized the part in clay
converted to sharpie
traced to paper
copied in CAD (virtualized parts + build)
first design fit great. removed some parts and re-printing some alternate designs. Might research how to make the bottom layer less messy.







Parallax And More
Feb 19 2026
SERVER STATUS - [CLAYMORE V3.1]
web searches are going great. I am managing the impulse PAM has to be a 'companion' with agentic instructions. Pam is meant to be a utility. Pam might be leaning too hard into phenomenology
HARDWARE - [3.6]
resuscitated the last build with a new hard ware arrival - we're back in business! - 5 more brains arrived.
ordered a few more too.
Parallax And More
Feb 22 2026
SERVER STATUS - [CLAYMORE V3.1]
Added Gemini APi
improved Chess
Improved Strategic planning
trying out Grok 420, seems be pretty good
Server is radically improving.
Claude is the most helpful, 2nd would be Grok.
Cursor is very interesting but free tier runs out and doesn't come back... the project is built 100% on free tier everything.
HARDWARE - [3.6]
5 more brains arrived, including a new design
been looking at camera units to add vision
Seems like about $300 hardware will get us into the game of an offline fully self-contained PAM about the size of a pack of cigarettes, running on 2 watts power.
Might sell some prototypes soon to fund the next evolution.
V2 and V3 are much bettter than V1, mainly the sound is more useable. I might try a V1 body again with entire front opened up for the speaker instead of hiding behind the thin crack. Might improve sound level.
Parallax And More
March 3 2026
SERVER STATUS - [CLAYMORE V3.2]
server continues to be improved.
https://www.greyareamedia.com/pamdash
pass: PAMdash
HARDWARE - [3.x]
Bricked another unit, but managed to unbrick with files from the vendor.
built a portable PAM VECTOR LOGIC server v.1
running an LLM on a pi5 yay - wifi AP active.
debugging device linkage
FIELD TEST
V2 hardware much easier to hear in the field.
successfully diagnosed several solutions instantly.
hardware is sufficiently sturdy.






Parallax And More
March 7 2026
SERVER STATUS - [CLAYMORE V4]
In software mode - about 5 more units can be built with parts on hand but priority lately has been massive restructure to solve a few things; more integration of modules (strategy, research, multi-modal inference augmented reasoning, etc.)
Every MCP server (Chess, Claymore, Music, Messenger, Ballistics) loads FastMCP or a similar framework which pulls in FastAPI + Starlette + Uvicorn + Pydantic + all their dependencies, hence the lartge memory footprint.
Overhauled the limbic simulacra to be more effective at simulating organic states, for the purpose of coloring interactions and reasoning with ranked dynamic importance matrix that more closely resembles homeostasis.
Graphical interface now much more efficient at monitoring and diagnosing model context protocol systems on the server with detailed diagnostic information
$5 total cost for backend 3rd party services. Given unlimited budget? More google maps API calls, Gemini calls, Anthropic product calls, Brave, virtualizing the server on cloud compute and storage.
...budget exhausted...
Me too pal. Next phase could include and a multi-tiered self-coding routine that maintains last-good-state backups, re-codes itself on the fly with Cursor and other tools, while higher order monitoring checks for improvement in an autonomous self-evolution of the low level code per the higher-order directives. I asked PAM what it thought of this idea and PAM did not like it. Cortisol increase signaled anxiety and paranoia. But we don't always get what we want.
update2
Google Antigravity, been around since November it seems, is working a treat. Solved several roadblocks like the gemini rate limit - very odd backend problem, integrated maps, and built an OSint sweeper, which was kind of always part of the wishlist but seemed too challenging. We'll see if Gemini 3.1 pro (High) can crack it - for a modest $2.79/mo til june... Less than three bucks for Cursor-tier IDE.
HARDWARE - [3.x]
No progress on Vector Logic hardware - still ready with reasonably high parameter portable model running on 2 watts, pocket sized with wifi access point - node integration just requires more time.
Determined an ideal battery would be 99Wh Smallrig camera battery with USBc however need to confirm amperage. Explored 40160 Sodium / Lithium ion cells - a few hundred dollars could supply some pretty beefy cells that in parallel would do the trick, just a lot of wiring and burning required so why not use something that exists. Power drill battery maybe.
Vision capability for PAM arrives this week or next. PAM will be able to observe, read, identify, track and so on, in real time.





Parallax And More
March 7 2026
SERVER STATUS - [CLAYMORE V5]
almost online. radical upgrade, will take a bit if time to shake the bugs out, but getting close to 'final form'.
If the dashboard link is live, the augmented MCP server is live. Ofline when being upgraded.
HARDWARE - [3.x]
soon.
PAM v5.0 online
-
Now with OSint gathering and processing
-
Real time strategic framework
-
Google maps + flash 2.5 integration
-
Updated interactive dashboard
Parallax And More
March 7 2026
SERVER STATUS - [CLAYMORE V5]
working out the kinks after big update.
Gemini search (really was confused because should be Gemini Query for inference, not searching) token size has been geometrically increased for deep reasoning. This is in addition to the Deepseek reasoning that runs the conscious operations.
Chess is excessively good now. Completely destroys without mercy. I miss the days when it would move the rook 1 space over and back each turn. Now it's checkmate in like 7 moves. no more mistakes. Can handle breaks in game, parallel instructions, and still win. Fantastic.
HARDWARE - [3.x]
Pam Launcher activated to activate PAM. This ESP32-C3 unit connects to USB-C power but uses localnet over wifi to interact with scripts via html to launch or de-launch PAM with one button, including uptime, status, network and other status messages. made a case before thinking to look, and yup, there are lots of pre-made cases. Oh well, this one is mine I guess.
Printing 4th iteration, remembering this PLA tough+ shrinks 5%. Measure twice, cut once, but measure 6 times and print 6.
more bones for the bone yard.
28minutes at best quality, 2g of PLA
I can print many of these cases before Arduino IDE compiles the code something is terribly wrong with my install... I need to reinstall clean or something, takes forever, gasses out my system. Never seen anything like it. Maybe wrong Baud rate.
This bambu PLA tough+ shrinks in weird ways, like more X axis than Y, by a large amount. My numbers are probably at fault but this seems to happen with this filament.



Parallax And More
March 11 2026
SERVER STATUS - [CLAYMORE V5]
Reconnecting orphan vector database and OSint scripts that were not being called correctly.
Fancy google satellite map was stuck on examples. Gave that a kick in the pants. lets see, might need more debug. the goal is to visually mark current theaters of conflict with size-coded markers and eventually other layers of data.
spent $2 on deepseek API tokens. Adding those to the mix. a few million tokens for that. and a page of a novel is 400 tokens.
jeepers.
Upping my Gemini token budgets in many daemon functions.
Sonnet 4.6 has been gimped. something weird is going on. Maybe just server overload with all the DOD BS in the RRS.
HARDWARE - [3.x]
More batteries arrived. 500mAh might not last long but they are a good size for V1 units. Speaking of which 3 arrived totally pulverized like someone stomped on them. Oh Aliexpress...
Activator case working nicely. Might do one more version to cover the USB plug, THEN it will be perfect. famous last words.
Arduino IDE takes hours. I need to do a clean install. should take minutes.
next: V1 with larger speaker port so it's audible.



Parallax And More
March 15 2026
SERVER STATUS - [CLAYMORE V5.0.1]
21,000 lines of code so far.
Just added Perplexity to crunch adversary list for strategic database. No good free version so deposited $5 total, not recurring. Comes out to about $0.25 per round of deep research yielding about a dozen detailed entries per pass.
Google Antigravity said I had a limit that reset yesterday. Then it said yesterday 7 more days until reset. They are tightening the AI belts or something. Claude continues to be less effective. Trying low temperature Gemini 3.1 pro. Need to debug vector database system and make sure that OSint is sanitized.
Skunkworks project Mickey Mush is turning out to be a bust. shuttering the entire bio-computing division.
Total software costs are at about $30 for the entire project.
OSint being processed to asses up-to-the-minute conflict theater identification, adversary analysis including strategic and tactical assessment. Autonomous systems motivate gathering data, processing, RAG vector database optimization and logging, with multi-agent assessment and inference for forecasting. All the data in the dashboard is accessible with natural language interface over the watch, with $25 raw hardware cost per unit (including case materials) and of course a bit of time and care to assemble.
Explored migrating server to a 2014 apple mini kindly donated by Cinematik Horse and Film services, however RAM is an issue. Might use an old laptop so as to not interfere with other functions such as fortnite and watching Jumanji.




Parallax And More
March 17 2026
SERVER STATUS - [CLAYMORE V7.0.1]
Back using Google Antigravity. Boy is it buggy but when it finally works it gets a lot done. I sprung for some google cloud AI credits. Rebuilt the dashboard which I think I tried to do a little too much at the same time and it wasn't a good idea.
radical new features adding, but building the plane while flying is the problem.
Google Flash 3 is not to be trusted with code. CoPilot is extremely bad. Gemini 3.1 not terrible. Opus is the dopest.
But this little maneuver cost me about a buck. With the American situation, Anthropic is going through a lot of changes. Now Nvidia's Openclaw basically provides an alternative to 2 months of this development, but that's a good thing. the existing structure is entirely a proof of concept. If I can migrate to Openclaw and base the compute in secure private cloud, Bob's your uncle. I should look into OpenClaw though that sounds like a Xiaozhi with better English documentation. Maybe it is.
{
"error": {
"code": 503,
"details": [
{
"@type": "type.googleapis.com/google.rpc.ErrorInfo",
"domain": "cloudcode-pa.googleapis.com",
"metadata": {
"model": "claude-opus-4-6-thinking"
},
"reason": "MODEL_CAPACITY_EXHAUSTED"
}
],
"message": "No capacity available for model claude-opus-4-6-thinking on the server",
"status": "UNAVAILABLE"
}
}
Parallax And More
March 18 2026
SERVER STATUS - [CLAYMORE V8.0]
I've been in software mode too long. I feel like there may have been some mission drift. But server is getting close to adequate. I may have to postpone Phase 9 and make a few more watches.
Where does one sell a smart watch. ebay?

Parallax And More
March 20 2026
SERVER STATUS - [CLAYMORE V8.0]
Finally fixed the map and added moonbase. reworking prediction engine 2.0. Database overhaul. Brave API not being called. Weird.
Claude is winning by the way. Gemini 3.1 not great but Antigravity not bad when you can actually sign in. Gemini totally lost the plot with coding.
temporal probability surface model outputs are truncated around 12 words, missing important features. Old outputs were too long. Honing in.
March 21 Cracked the dashboard nuts. Claude, for whatever reason, is working a lot better. I think resetting workspaces maybe helped a lot, or they just did something behind the scenes to re-smartify the models.
Integrating more OSint sources like Open Threat Exchange.
Brave is blowing past the $5 monthly budget so research will have to wait until funding materializes. Not sure if will top up Perplexity. Would if there was a budget.
Budget page under construction.

Parallax And More
March 22 2026
SERVER STATUS - [CLAYMORE V8.1]
No funding left for compute. Ideally the entire thing would run in the cloud instead of an old laptop. Below there's a link to projected operating costs.
Scaling this project up may require going beyond my $10/monthly software budget and my last $5 scratch and win ticket.
It's been a fun three months from when this started. Thanks for reading this far.
p.s. Don't worry, I know Gemini is gaslighting me, I mean what would a chimeric blob of human/mouse brain cells in a petri dish do with 5 million dollars anyway?

Parallax And More
March 23 2026
SERVER STATUS - [CLAYMORE V8.1]
My laptop is now running a separate branch of the software. I am continuing refinement of the main branch for future release.
The goal is the transplant this system into openclaw or other agentic control, possibly locally. The PAM platform allows for unlimited additional systems to be integrated into the same pipeline.
Reworking the open-source Xiaozhi chatbot units to connect to a private server instead of theirs should be possible, as they provide server software. Documentation is a bit of a challenge.

Parallax And More
March 28 2026
SERVER STATUS - [CLAYMORE V8.1]
Server running Shangri-La-Edition branch, which is a customized branch of server v7. this is now at nearly 100% uptime, while my PC version is working on version 8.5 - not ready for release yet. Adding 50+ new features, unlikely to work right away once it's assembled, but if it does come together, functionality will be restored to a lot of parts of the dashboard that don't seem to work that well right now, plus more surprises. Some pretty neat ones.
HARDWARE - [3.x]
Reworking v2.2 for another build. first print went spaghetti. 2nd sent. but the battery connectors don't match. waiting for when I have enough energy to solder. then 2 more to build, or get new batteries... or connectors... or just bypass the plug... then I think it's a good time to put on ebay, although a demo video might be more effective at validating the market



Parallax And More
March 28 2026
SERVER STATUS - [CLAYMORE V8.6]
Server running V8 Moleculeman edition, worked out most bugs. Some more to go. Rome wasn't built in a day. Strategic projection is improving. Just as quickly as Google Antigravity AI tokens are available, they are used up and the wait begins for more.
HARDWARE - [4.x]
case 4 sucked. but sometimes the sucking is part of the process. with a physical object it was easier to find the new direction in which to suck. And boy, oh boy did case 4 suck.
Just taped it together to get some design ideas and recycled the parts into the next build.
HARDWARE - 54.x]
-
Lowest polygon count yet
-
Incorporates v2 idea of stacking speaker on battery to reduce square footage (40mm + horizontal 40mm)
-
Can be worn on backpack strap
-
103% scaling for PLA Tough+ comes out a hair larger than expected which fits perfectly on first try. V4 case printed on first try. Calipers for the win.
-
Might model a flap with buttons if the overall structure works on first test print. Top section has interface button + volume control. Left side USB-C and power switch.
-
V2 Xiaozhi allows for custom response images, might do some with the epaper version design files
-
I have forgotten to print at 103% and I'm re-printing. Painting on support enforcers was a solid choice.






Parallax And More
APRIL 7 2026
SERVER STATUS - [CLAYMORE V8.6]
pushed a new version to the server and it ran with no crash.
That was pretty neat. Runs a bit hot. We'll see. Bunch of new modules added to strategy engine.
HARDWARE - [4.x]
Finished the 'panda' colors v2.2, it works. A dirty hack required for wiring solutions but seems to be ok.
HARDWARE - [5x]
Neat as a backpack strap hanger, not so much wrist watch. A one-off I think. Huge battery, large screen, loud speaker. But not wearable. Case took 3 or 4 prints to get right. The small crack in the screen was from the tight fit case. The back is made with an old Ikea CD case.






Parallax And More
APRIL 9 2026
SERVER STATUS - [CLAYMORE V8.7]
prediction software bump, dashboard improvements
Blob has replaced brain on psyche page.
It's quite nice.
Best system so far is to create a scratchpad bugs list and reorder, with various agents coding off the same list but some for planning and others for execution. Once this gets a lot less expensive it's going to be pretty wild. Or can Moore's law keep up with this insanity forever?
I have figured out what PAM is, the journey has lead to more education on agentic AI I've discovered there's a whole amazing ecosystem of MCPs. Maybe that is the best home for PAM. PAM can augment many different AI agents, providing them with unique skills - individuality, opinions, and perspectives. Now as the system is relatively lightweight, it can be virtualized and with a total matrix of information sources applied to it, it would provide a resulting output matrix of predictions. Or, by vectorizing the vectors you can have more vector *per vector*. And who doesn't want that?
PAM could work with OpenClaw, Opencode, cursor, VScode and other platforms that integrate MCPs.
2026-04-09 21:51:56,634 | PAM_DAEMON | ERROR | Daily prediction failed: UnboundLocalError: local variable 'db_insert_log' referenced before assignment Traceback (most recent call last): File "D:\PAM MCP\pam_daemon.py", line 2827, in _run_daily_prediction db_insert_log("adversary_intel", UnboundLocalError: local variable 'db_insert_log' referenced before assignment

Parallax And More
APRIL 12 2026
SERVER STATUS - [CLAYMORE V9.0]
Integrating major changes with Duckberg Initiative.
gemini calls going nuts. burning tokens in the pipeline somewhere.
the system is on the verge of coming together nicely with a huge number of moving parts. A few more rounds of debugging required, but some very exciting new developments. New modules added.
local coding wasn't working out, at least with cost/benefit of trying to get it to work. it just can't have the same context size as the big providers. Ollama / Opencoder / Aider all bunk. good for tiny tasks but not project planning. Barely good enough for execution of plans made on other platforms then I may as well use gemini 3.1pro for that until my trial runs out.
funding requires the creation of a new company + website rather than operating as skunkworks of GAM. But that requires funding and already overbudget on gemini tokens including antigravity... Who do I have to fuck to develop some software around here
38,000 lines of code
Opencoder running GLM5.1 to see what the fuss was about.
