The original thread can be found here: https://trashchan.xyz/robowaifu/thread/595.html --- Welcome to the Lemon Cookie thread, The goal of Lemon Cookie is to create a framework where a synthetic "mind and soul" can emerge through a "LLM as cognitive architecture" approach. This thread exists to collect feedback, ask for help & to document my progress. First I am going to try to give a high level overview of how this cognitive architecture is envisioned and the ideas behind it. I have spent time looking at cognitive architecture work, in the field there is now a consensus on how the mind works at a high level. An important mechanism is a "whiteboard", basically a global temporary memory that all the other systems read in and out of. Then there is different long-term memory systems that react to and add content to the whiteboard. Along with memory pattern matcher(s)/rules work on the content of the whiteboard. A key thing to consider is the difference in philosophy that cognitive architecture projects have, the intelligence is considered to emerge from the entire system. Compare this to LLM agent work where it's considered the intelligence is the LLM. My feelings on the general LLM space are conflicted, I am both amazed and really disappointed. LLMs possess an incredible level of flexibility, world knowledge and coherence. But everything outside of the model is stagnant. It's endless API wrappers & redundant frameworks all slight permutations on RAG & basic tool calling. I will believe that LLMs are misused as chatbots, simply put their pattern matching and associative power is constrained by chat format and shallow tooling. In the Lemon Cookie Cognitive Architecture so far here are the important aspects: 1. Memory is difficult. I do not think there is a singular data structure or method that is able to handle it all, several distinct types of memory will be needed. So far I plan for a PathRAG like system and a "Triadic Memory" inspired system for external associations (this is missing in most LLM solutions). 2. LLM as Kernel, The LLM's context window is the Whiteboard and has a REPL like mechanism. It holds structured data and logic in scripting-like format so it's both LLM & Human readable while staying easy to parse & allows for expressive structured data. The LLM's role will be to decompose data and make patterns and associations explicit as executable statements. 3. The language has to be LLM/CogArch-centric. There is a thousand ""agents"" that give LLMs a python interpreter as a tool. The two need to be more tightly coupled. Scripted behavior via pattern matching, The whiteboard is a bag of objects, this allows for programmable pattern matching (think functional programming like Haskell). It's also important to allow the LLM to observe code execution and to be able to modify state and execution flow. Data in languages have scoping rules, so should LLM context. Etc... I will go into more depth about the language in another post. 4. Another important system is the "GSR" Generative Sparse Representation and it will be a first class language & runtime type, This also needs its own post. But in general I am inspired by two things, "Generative FrameNet" paper where an LLM & an embedding model is used to automatically construct new FrameNet frames. The second source is "Numenta's SDRs"/"Sparse distributed memory" this representation has a lot of useful properties for memory (Please watch the videos under the "What the hell is an SDR?" segment in my links list for an easy introduction.) I think SDR unions & SDR noise tolerance will be especially useful. 5. A custom model, For all of the above to work well, a model will need to be fine tuned with special behaviors. I do want input on this. Baking facts & behaviors into LLM weights is costly, creating bloated models that are hard to run or train (why memorize all the capitals?), while letting authors gatekeep truth and impose "safety" detached from context. Blocking role-play "violence" or intimacy isn't protection: it's authors hijacking your AI companion to preach at you. Externalizing behaviors via whiteboard pattern matching shifts control: stabbing you in-game can be funny, but a robot wielding a knife isn't. Maybe you want intimacy privately, but don't want your AI flirting back at your friends. When put together I think this will be able to host a kind of synthetic "soul", In a living being what we call a personality is the accumulated associations, learned behaviors, beliefs and quirks molded by a unique set of experiences. I hope this will be true for this system too.

I realize it's a bit grandiose (though probably no more than the whole idea of creating a irl robowaifu in the first place) but I want to begin thinking about how to create a working robowaifu 'brain', and how to create a special operating system to run on her so she will have the best chance of remaining an open, safe & secure platform. OS Language Choice C is by far the single largest source of security holes in software history, so it's out more or less automatically by default. I'm sure that causes many C developers to sneer at the very thought of a non-C-based operating system, but the unavoidable cost of fixing the large numbers of bugs and security holes that are inevitable for a large C project is simply more than can be borne by a small team. There is much else to do besides writing code here, and C hooks can be generated wherever deemed necessary as well. C++ is the best candidate for me personally, since it's the language I know best (I also know C too). It's also basically as low level as C but with far better abstractions and much better type-checking. And just like C, you can inline Assembler code wherever needed in C++. Although poorly-written C++ can be as bad as C code in terms of safety due to the necessity of it being compatible with C, it also has many facilities to not go there for the sane coder who adheres to simple, tried-and-true guidelines. There is also a good C++ project already ongoing that could be used for a clustered unikernel OS approach for speed and safety. This approach could save drastic amounts of time for many reasons, not the least of which is tightly constrained debugging. Every 'process' is literally it's own single-threaded kernel, and mountains of old-style cruft (and thinking) typical with OS development simply vanishes. FORTRAN is a very well-established language for the sciences, but a) there aren't a lot of FORTRAN coders, and b) it's probably not the greatest at being a general-purpose language anyway. I'm sure it could be made to run robotics hardware, but would probably be a challenge to turn into an OS. There are plenty of dujour SJW & coffee languages out there, but quite apart from the rampant faggotry & SJWtardism plainly evident in most of their communities, none of them have the kind of industrial experience and pure backbone that C, C++, or FORTRAN have. D and Ada are special cases and possibly bear due consideration in some year's time, but for now C++ is the obvious choice to me for a Robowaifu OS foundation, Python probably being the best scripting language for it. (1 of 2) >=== -fmt cleanup

Cheap and easy 3D printing is vital for a cottage industry making custom robowaifus. Please post good resources on 3D printing.

www.3dprinter.net/
https://archive.is/YdvXj

/meta, offtopic, & QTDDTOT <--- Mini-FAQ A few hand-picked posts on various /robowaifu/-related topics: --->Lurk less: Tasks to Tackle ( >>20037 ) --->Why is keeping mass (weight) low so important? ( >>4313 ) --->How to get started with AI/ML for beginners ( >>18306 ) --->"The Big 4" things we need to solve here ( >>15182 ) --->HOW TO SOLVE IT ( >>4143 ) --->Why we exist on an imageboard, and not some other forum platform ( >>15638, >>31158 ) --->This is madness! You can't possibly succeed, so why even bother? ( >>20208, >>23969 ) --->All AI programming is done in Python. So why are you using C & C++ here? ( >>21057, >>21091, >>27167, >>29994 ) --->How to learn to program in C++ for robowaifus? ( >>18749, >>19777 ) --->How to bulk-download AI models from huggingface.co ? ( >>25962, >>25986 )

>order companionbot from obscure japanese website
>you're not a pedo, but size is a major factor in the practicality of these designs, so the loli-robot is by far the cheapest and most reliable option
>you open the box and find your companion, purposely designed to look like a cartoon robot, rather than a real person
>still, the robot's purpose is obvious when you realize it is nude and has genitals
>since it is a lolibot, you, a 32 year old wizard NEET, can't exactly go to the store and buy clothes that fit it. So you'd better do an extra good job at hiding it from any guests that come over.
>lol you never have any guests. Guess some problems solve themselves.
>before turning the robot on, you have to setup the software options on your computer. You adjust a series of sliders regarding personality traits, before selecting the English option, and choosing your preferred voice from a list.
>then you agonize for hours over picking a name
>other, more expensive models, are wi-fi compatible, but you purposely chose the cheapest option with no wireless connectivity, not just because you're cheap, because you don't want people spying on your waifu
>you save the settings to a flash drive which is inserted in the robot's navel, after removing a waterproof cover, of course. But this is when you realize you don't actually know how to turn the robot on
>after rifling through the manual you find the on/off procedure, which involves bending the fingers into a certain configuration before pressing in the port on the robot's navel with one hand and pinching the buttons that are the robot's g-spot and clitoris with the other.
>the robot immediately comes to life, opening its eyes and looking directly at you, in a rather compromising position
>Your sudden reaction of shock abides when you remind yourself that it's simply a robot.
>But the awkwardness comes back when the robot speaks, in very broken Engrish
>still, you can understand as it introduces itself with the name you've given it, the voice you chose for it.
>you know that you chose those options, but when the robot asks you for your name, you still answer just as awkwardly as when a real girl would ask you your name at the bank or whatever
>actually, more awkwardly because your fingers are inside it. So you freeze up, as you do even in simpler situations
>but the robot is programmed for your happiness, and detects your stress, smiling at you in an attempt to make you feel better. But only briefly, because you programmed it with just the mildest hint of tsundere
>it tells you to not feel stressed, and assures you that it is not being damaged by your touch
>you remove yourself from the robot's vagina, and notice a brief, subtle shudder. Nice attention to detail from the creators
>You stand up in front of the robot and watch it as it looks around the room, studying its surroundings. It moves in an unnaturally smooth motion, but manages to not be too uncanny due to looking like a robot, rather than a human.
>as the robot's eyes scan the room, you notice that they stop for just a tiny but longer than usual as they look straight ahead. Straight ahead at your boner, which happens to be right at the small robot's face level.
>once again your mind forgets that you are dealing with a machine, and you awkwardly try to create small talk to diffuse the situation, asking the robot if it requires anything else at the moment. It declines, and instead asks if there is anything you desire
>you, the autist you are, refuse to let the robot do anything for you, and instead say that you are going to go and make a sandwich.
>you tell the robot to make itself comfortable, then cringe to yourself when you realize the absurdity of that statement.

(1 of 6)

Material Science & Production This thread is dedicated to all aspects of material sciences in robotics. This includes production methods for creation, processing, and manipulating materials to attain desired results. Our future robowaifus must be built using materials we can attain and sculpt into them. Let's work together to build the future. Consider picrel, what materials would you use for her shell? Her skeleton? Consider mechanical properties, density, how they would feel to hold. All are important aspects we must consider. This thread will have overlap with the 3D printing thread. Feel free to crosslink at will. This thread is made as a merger of 2 previous material threads and a CNC thread.

Creating robowaifus requires lots and lots of design and artistry. It's not all just nerd stuff you know Anon! :^) ITT: Add any techniques, tips, tricks, or content links for any Digital Content Creation (DCC) tools and training to use when making robowaifus. >note: This isn't the 'Post Your Robowaifu-related OC Arts & Designs General' thread. We'll make one of those later perhaps. >--- I spent some time playing with the program Makehuman and I'll say I wasn't impressed. It's not possible to make anime real using Makehuman, in fact the options (for example eye size) are somewhat limited. But there's good news, don't worry! The creator of Makehuman went on to create a blender plugin called ManuelBastioniLAB which is much better (and has a much more humorous name). The plugin is easy to install and use (especially if you have a little blender experience). There are three different anime female defaults that are all pretty cute. (Pictured is a slightly modified Anime Female 2.) There are sliders to modify everything from finger length to eye position to boob size. It even has a posable skeleton. Unfortunately the anime models don't have inverse kinematic skeletons which are much easier to pose. Going forward I'm probably going to use MasturBationLABManuelBastioniLAB as the starting point for my designs. --- Saving everything with yt-dlp (>>16357, >>12247) >===

Tensegrity Thread Tenssegrity is the purposeful application of tension in a system of non-contact components to provide integrity. These components effectively float on compression provided by tension elements. Tensegrity structures are often formed via rigid rods with a cable defining the spatial relations of the system. Picrel 1 is NASA’s Super Ball Bot, which uses the common 6 bar structure. By altering the lengths of the rods, the “ball” can roll. Please see (https://www.nasa.gov/image-article/super-ball-bot/) Our bodies use tensegrity to provide us with incredible strength, durability, and adaptability. Consider how when you bump into something or fall, you can feel the pressure dissipate throughout large parts of your body. This is due to your muscles, fascia, ligaments, etc… transferring the force throughout your body, protecting the impacted part. You can walk with little effort thanks in part to tensegrity. Your legs joints are all floating, providing low friction movement while distributing the force of impact throughout your entire leg when you step. Please see (http://intensiondesigns.ca/geometry-of-anatomy/) Tensegrity can also be made with elastic elements. These structures are what I believe are best suited for our endeavors. They provide looser tolerance requirements and give her body some squeezability. By incorporating naturally stretchable elements, she can better withstand having an Anon using her. (I speak from experience, though I still broke that torso before taking pictures.) Though there are drawbacks. These designs are deceptively difficult to design correctly. Our requirements for external aesthetics provide unique design requirements that complicate the design phase. I still believe using this concept is objectively correct for us to pursue. A good example to build off of (Debatable whether or not it’s true tensegrity): https://www.thingiverse.com/thing:4182634

Post your prototypes and failures. We fail until we win. Don't forget looking through the old threads here >>418, >>18800 and >>21647 to understand how we got to where we are now.

For the most of 2024 and until now, I have been working on my own robowaifu design. I call her Galatea. The design is very easy to build with the instructions and files, and is relatively very cheap, less than $400 to make. It's also very customizable, you can choose the color, dress, hair, and even AI. I intend this to be the Model T of humanoid robots and robotic companions, while it is not the most complex, it is easy to mass produce and cheap. The updated design makes the legs more proportionate, and a new head that's more anime styled, to increase cuteness. I also have a new robot base that's more powerful.