/robowaifu/ - DIY Robot Wives

Advancing robotics to a point where anime catgrill meidos in tiny miniskirts are a reality!

We are back again (again).

Our TOR hidden service has been restored.

Max message length: 6144

Drag files to upload or
click here to select them

Maximum 5 files / Maximum size: 20.00 MB

Captcha
no cookies?
More

(used to delete files and postings)


“There is no telling how many miles you will have to run while chasing a dream.” -t. Anonymous


Open file (58.56 KB 1244x2374 MaidComFront.jpg)
Open file (39.04 KB 1244x2318 MaidComSide.jpg)
Open file (56.65 KB 1244x2318 MaidComBack.jpg)
MaidCom Kiwi 02/08/2024 (Thu) 06:40:01 No.29219 [Reply] [Last]
MaidCom Project Thread 2 Project Goal: Simple, low cost, extensible platform for robowaifu development. Picrel shows the model which is being developed. Every part will be designed to be easily printable and replaceable. Her designs will be open source. Modding and customization will be encouraged. This is a base model. Early revisions will be heavily limited in functionality. I invite you to help design and define standards so that it is easy to create specialized add-ons to allow her to become your own waifu. Collaboration is important, MaidCom is officially partnered with Lin and his Waifu Wheelchair, if you'd also like to be officially partnered, say so. Cat eats and miniskirts are encouraged! <--- Previous thread: ( >>15630 ) >=== -add crosslink
Edited last time by Chobitsu on 08/14/2024 (Wed) 21:50:13.
190 posts and 130 images omitted.
Open file (83.85 KB 584x934 Maid.png)
Open file (82.90 KB 584x940 Optional bobs.png)
Decided to simplify her main body and leave the bobs and buns as optional add-ons. Hard plastic bobs are painful to snuggle with from my personal experience in recent experiments. Decided her joints should be modular and optional too. MaidCom is going all in on the simplest core that you expand as you like. What connector should she use? I've been thinking USB C for electrical with pegs and sockets for the physical connections. If an open standard already exists, I'd like to make her as compatible as possible, Modularity to fit specific niches is the goal. I recently asked normies what they wanted MaidCom to do. Laundry and washing dishes were the number one asks. When I said no robot on Earth can do it, they said I asked what they wanted, and that was it. So, I came to the conclusion that she needs to do that. But, those tasks are supremely difficult for humanoids. She needs to be able to adapt to meet those demands, in the specific situations of her user. It's impossible to make her universal and affordable, she needs to be personal.
>>42954 POTD >I've been thinking USB C for electrical Probably a safe bet for this revision. I'd say just go with that. You can devise other revisions at a later point in time. >When I said no robot on Earth can do it >she needs to be personal. Start there. DO.NOT. get hung up trying to overreach at this stage. >tl;dr Start smol; grow big. You're doing great, Kiwi! Looking forward to meeting dear MaidCom at Christmas! Cheers. :^)
>>42954 I like the modular and standardized design. >he needs to be able to adapt to meet those demands, in the specific situations of her user. I'm really curious to see how that can be done with consumer technology. You may leapfrog our tech by a few years at least. >she needs to be personal. Exactly
Open file (101.89 KB 706x886 MaidComCrunch.png)
Successfully designed her waist articulation system. Will be working on her leg/arm articulation system tomorrow.
>>43162 Beautiful. I'm gettin' excited, Anon! :D

Robowaifus in Media: Thread 03 GreerTech 09/10/2025 (Wed) 07:54:46 No.41434 [Reply]
Post about whatever media predominately features at least one fembot aka gynoid (female form of an android) as an important character, ideally a robowaifu or synthetic girlfriend. Some freedom with the topic is allowed, virtual waifus or bodiless AI might also qualify if she is female. Negative framing of the whole topic should be mentioned with negative sentiment. Cyborgs with a human brain or uploads of women don't really fit in, but if she's very nice (Alita) and maybe not a human based cyborg (catborg/netoborg) we can let it slide. Magical dolls have also been included in the past, especially when the guy had to hand-made them. Look through the old threads, it's worth it: >>82 >>18711 - Picrel shows some of the more well know shows from a few years ago. I made a long list with links to more info's on most known anime shows about fembots/robowaifus, without hentai but including some ecchi and posted it here in the old thread: >>7008 - It also features some live-action shows and movies. I repost the updated list here, not claiming that it is complete, especially when it comes to live action and shows/movies we don't really like. >In some cases I can only assume that the show includes robogirls, since the show is about various robots, but I haven't seen it yet. A.D. Police Files: https://www.anime-planet.com/anime/ad-police-files Andromeda Stories: https://www.anime-planet.com/anime/andromeda-stories Angelic Layer: https://www.anime-planet.com/anime/angelic-layer Armitage III: https://www.anime-planet.com/anime/armitage-iii Azusa will help: https://www.anime-planet.com/anime/azusa-will-help Blade Runner 2022: https://www.anime-planet.com/anime/blade-runner-black-out-2022 Busou Shinki: https://www.anime-planet.com/anime/busou-shinki-moon-angel Butobi CPU: https://www.anime-planet.com/anime/buttobi-cpu Casshern Sins: https://www.anime-planet.com/anime/casshern-sins Chobits: https://www.anime-planet.com/anime/chobits

Message too long. Click here to view full text.

12 posts and 4 images omitted.
>>43116 Heh, that's all true. Good points, GreerTech. Cheers. :^)
Open file (237.04 KB 659x1352 Alma.png)
Open file (281.78 KB 800x1352 Machina.png)
Open file (1.21 MB 2313x1671 AlmaLapPillow.jpg)
Alma chan Wants to Have a Family! This show is packing heaps of cuteness! It's a fun goofy slice of life story of a family where the daughter is a super robot. It feels highly episodic. Alma and Machina are the main robot girls. Though they're generally depicted as tiny, roughly ~130cm ~4ft, their bodies are accessories. Only their heads are the real body. Picrel 3 shows Alma with an adult body that either of them can use. It's a silly show but, Alma with an adult body is the best robot girl this season.
>>43149 >Only their heads are the real body. Huh, funny enuff that's how SPUD and Pringle are going: both having their raspi's in the noggin and connect via peripherals (so far just I2C)
>>43149 Thanks for the info Kiwi.
Open file (161.79 KB 850x1186 AlmaBunny.jpg)
>>43151 I do like the concept, helps with modularity

HAPPY BIRTHDAY /ROBOWAIFU/ Robowaifu Technician Board owner 11/27/2019 (Wed) 17:27:05 No.1591 [Reply] [Last]
9th Birthday Edition greeting here: ( >>43098 ) --- >original (albeit a bit edited) OP follows: Well it's Thanksgiving time again and that means it's /robowaifu/s birthday time too. It's been 3 full years since we began, and this last one has been a bit of a ride tbh. With the deplatforming of 8ch all of us who had communities there were mostly left out in the cold. Thankfully we've been given a new home here in our bunkerhome at JulaynuJulay, and a few of us have found our way back together here. Hopefully the rest of us will find Julay, and /robowaifu/ again as well. We've also made some new friends since we've been here, and I think we're in pretty good shape all things considered. On the topic of deplatforming, we have a new archival system in action that keeps a copy of the board up to date on my machine. Note that my original intent was to fully automate the archive.today archives, but it hasn't worked properly (they seem to be fighting against bots pretty hard now). I hope at least one other of you will also join in for the approach that's actually working, and use BUMP to keep at least one other copy of /robowaifu/ safe in addition to my own. You never know what might happen to my gear (or even to me), and it's just smart thinking to have at least two of us keeping this board safe. My intent is to finish up the system for board migrations (along with Robi), and then bring over other things from the old files and get this board in shape again. Then we can keep it fully backed up together. As you regulars know, /robowaifu/ is basically unique among imageboards and well-deserves preservation IMO. Any other takers for doing backups as well? I just use a cronjob and it's all fully automatic daily I never have to touch it. I'll explain everything in detail how to do it if anyone else wants to participate. One other thing; should anything ever happen to Julay, just regroup on Fatchan Anoncafe Trashchan in our bunker there. Actually, I'm pretty upbeat about both the world of IB communities in general, and our own /robowaifu/ in particular. We all took a hard knock a few months ago, but we're back on our feet and in the fight again. Kudos in particular to both Julay and Smug for their innovations with the webring introduction. It's lent a resilience to the underlying systems for all our various communities that we've never had before afaict. This alone should help to ensure we have a long future of shitposting together anons. Anyway moving on, I hope this coming year will also see a resurgence in everyone's posts here about their personal projects. I intend to do so myself. It's always a pleasure to see Anon's efforts and blog-posts about their current attempts and ideas, regardless whether they are successes or failures. Persistence is really the single most important factor for eventual success--even more than innate talent--and so just don't quit anon! Don't be afraid to get back in the game even if you met with failure before. Try something different this time, right?

Message too long. Click here to view full text.

Edited last time by Chobitsu on 11/30/2025 (Sun) 23:08:38.
122 posts and 50 images omitted.
Happy Birthday, /robowaifu/ ! It's been nine years since we began life as /robowaifu/ on Thanksgiving weekend. We have some new Anons onboard again this year. We're still waiting patiently for some old frens to reappear. As predicted, there is a veritable "arms race" ( >>34520 ) of humanoid development going on now ( >>43048 ). This will only grow for several years to come. ALSO as predicted, the first major corpo has stepped forward and displayed a gynoid : (cf. >>42698, >>42722, et al). This is a big deal! :^) Anons are moving forward apace with their own projects, and a years old new one has begun that yours truly will be participating in: HoloWaifu ( >>42840, et al). I'm really looking forward to see where we all go with this one! What an amazing turmoil this past year this has been for the AI LLM scene! Based DeepSeek (and dozens of other companies) have sprung up to challenge the (((status quo))). Cl*sedAI has been burning through taxpayer's & investor's cash like shoveling space freighters into a cosmic black hole! Along with the roller coaster NGr*edia has been through, popcorn has certainly intensified this year!! :DD <---> It's such a blessing to have all you Anons here on /robowaifu/ together. May this be the year of the waifu! :^) Keep Moving Forward.
>>43098 Happy 9th Birthday! I would say the year has gone by fast, but this year has been so hectic and event-filled, that it feels like 2-3 years. Here's to many, many more years of /robowaifu/ !
>>43121 Thanks, GreerTech! >this year has been so hectic and event-filled, that it feels like 2-3 years. I can see that! It certainly seems like an unusual one. >Here's to many, many more years of /robowaifu/ ! Amen, Brother. <---> Cheers, Anons. :^)
Happy 9th birthday!
>>43128 Thanks, Ribose! I hope your research and plans are moving forward apace. Cheers, Anon. :^)

ITT: Anons derail the board into debate about Christianity :^) Robowaifu Technician 04/02/2020 (Thu) 02:24:54 No.2050 [Reply] [Last]
I found this project and it looks interesting. Robots wives appeal to me because i'm convinced human woman and humans in general have flaws that make having close relationships with them a waste of energy. I'm a pathetic freshman engineering student who knows barely anything about anything. Honestly, I think current technology isn't at a place that could produce satisfying results for me at least. I'd like something better than an actual person, not a compromise. Even then the technology is there, I have my doubts it'll be affordable to make on your own. Fingers crossed though. Anyway, what kind of behavior would you like from your robot wife? I'd like mine to be unemotional, lacking in empathy, stoic and disinterested in personal gain or other people. I think human woman would be improved if they were like that. Sorry if this thread is inappropriate.
Edited last time by Chobitsu on 04/06/2020 (Mon) 16:00:20.
268 posts and 88 images omitted.
>>43026 TLDR: the human body is the soul's interface to the physical world: soul processes info given by the brain so if the interface is damaged so is the info. Like feeding info to an LLM: if there is some cheeky bugger sneaking in extra prompts your LLM gonna do some funky stuff.
I think bodies and "hardware" are vessels that "souls" operate through and manifest themselves through onto reality, and so the quality of the vessel enables more or less of the soul to manifest and act upon reality, so a damaged brain or body just limits how much the soul can be manifested, and better hardware whatever it may be enables more and a closer to full expression of the soul. >>43033 I wrote the above as this was posted, same thing. lingustic analogy: the soul is what's being said, the vessel is the language it is being said through.
>>43033 Exactly!
>>43022 ... My words speak for themselves, AFAICT. Meaning no disrespect, but I'm not sure what else you were expecting of me? >>43026 >Phineas Gage Intredasting. Along with @Mechnomancer (cf. >>43033 ), I consider the brain & other neural tissue to be the primary interface with the soul. As a firm substance-dualist, I consider the human soul to be part-physical, part-immaterial. (As opposed to our spirit being, which is entirely immaterial.) I'll also venture to say the obvious here: somewhere, somehow, the natural must have some border -- some interface -- with the transcendent. How that works is a mystery only God understands fully, IMHO. :^) >>43033 >Like feeding info to an LLM: if there is some cheeky bugger sneaking in extra prompts your LLM gonna do some funky stuff. Heh, amusingly-worded Anon. :D >>43034 >...and so the quality of the vessel enables more or less of the soul to manifest and act upon reality Thats a very interesting insight, Anon. :^)
> (Christian salvation -related : >>43136 )

/robowaifu/-meta-12: Angry About Elves Greentext anon 09/07/2025 (Sun) 03:23:09 No.41241 [Reply] [Last]
/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 ) --->Why shouldn't we use Cloud AI? ( >>38090, >>22630, >>30049, >>30051 ) --->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, >>37647 )

Message too long. Click here to view full text.

Edited last time by Chobitsu on 10/10/2025 (Fri) 04:43:57.
354 posts and 90 images omitted.
Some of the finest woodcraft engineering on these posts & beams & planks I've ever watched before: https://www.youtube.com/watch?v=trYsjl51Njs
Edited last time by Chobitsu on 11/30/2025 (Sun) 17:27:04.
Did St. Terry Davis ever share his thoughts on programming languages other than his own? I keep getting YouTube video recommendations about it, and I always see LISP called "God's programming language" but then, of course, someone always has to say that HolyC is actually God's language.
>>43115 I don't personally recall Terry ever having much of anything positive to say about any other programming language to my recollection, Anon. Everything but HolyC was niggerlicious to one degree or other. I think he begrudgingly acknowledged BASIC & C++ 's existences (the former b/c it was part of the Commodore 64, and the latter b/c it had a few good ideas beyond C * ). Maybe some other Anons here can chime in? I can't really think of anything else on this topic, other than to say the idea that TAD would call LISP of all things "godly" is quite laughable AFAICT. Cheers, Anon. :^) --- * He did pick up some C++ concepts to use inside HolyC.
Edited last time by Chobitsu on 12/03/2025 (Wed) 03:43:50.
Open file (3.37 MB 1024x1536 longhouseturtle.png)
>>43119 POTD Lel, GG. :D

Open file (51.12 KB 256x256 ClipboardImage.png)
Lemon Cookie EnvelopingTwilight##AgvQjr 04/28/2025 (Mon) 21:51:57 No.37980 [Reply]
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.

Message too long. Click here to view full text.

9 posts and 4 images omitted.
>>39162 >>AI research paper >Impressive. Please note the paper is not serious, I literally just wanted to share some AI output that came out ok. >>39223 >I finished the paper. Ehhhhh, it looks good and bad at the same time. I think it got some good big picture stuff but I'm not sure about the rest. Though I must admit much of the last of it is above my head. Thats the feeling I got from it too, Its good, but its also bad lol. I am amazed that it got the big picture and generated something so coherent, A year ago no LLM closed or open, framework or not would produce something of this quality. But there is also lots of gaps plainly visible. Don't take this PDF as actual plans, I just posted it for fun. ---- >>39162 >Am I understanding you rightly, Anon? If so wow that's a serious undertaking. Yes, but is it really such a big undertaking? I feel like most programmers eventually get the itch to do so, usually as a toy or some sort of DSL. In this case, it's a DSL, it's not replacing any of the systems level code, that is still being written in D and I am still using C & C++ libraries. >>39221 I am aware of NIM, it was one of the languages I ran into before I settled for D, I liked what I saw and if I was looking for a system language it would be high up on my list. I don't think it would make a good embedded scripting type language. >Now if this guy, wonderbrain, has trouble with C++ then, I have no hope. I come from C++, the reason I switched is because I do this as a hobby and I am a solo developer, so my productivity is the most important metric. C++ while powerful, I found to be more of a footgun to me. I spent more time then I wanted dealing with memory & lifetime issues, horrid cmake build scripts and etc... Because I am not a part of a team or have any obligations to make my self replaceable. I decided to move to something that makes me happier. I pick D because its like if C++ had nicer syntax, nicer templates & a garbage collector.
>>39228 >I literally just wanted to share some AI output that came out ok. Got it. I found that impressive. The claim "muh half the research papers today are written by AI!111" from neo-Luddites what a term :D may be partly-true soon. :^) <---> >Yes, but is it really such a big undertaking? Maybe its just """me and my fast-lightnin' mind""" talking, but yes, it certainly seems so to me personally. Given the literal multiple-trillions being spent yearly today on this general domain, I think market & economic pressures would've already arrived at effective solutions decades ago if it were a 'simple' thing. :^) >In this case, it's a DSL, it's not replacing any of the systems level code, that is still being written in D and I am still using C & C++ libraries. Good thinking. That's on a much-more feasible scale for a talented individual, I think. I myself hope to create a DSL wrapper of sorts for RW Foundations code: primarily as a way to ease/ensure-effective-support-for safe, standardized & encompassing scripting interfaces to our robowaifus (for a variety of other languages like, eg, Python & Lua). Kind of a Scripting Abstraction Layer over the underlying Executive/C4 realtime systems code. I predict this can eventually even be extended out to providing realworld, 'embodied' interfaces for LLMs, STT<->TTS, OpenCV, etc., into our robowaifus. :^) <---> >I really do hope that my choice of D does not upset him too much, I understand why he picks C++. Lol, no not at all. Though it is a bit discouraging to me that after almost a decade's dedicated-effort on my part trying to help newcomers here to learn the language, I still dont have.a.single. regular C++ collaborator here on /robowaifu/ with me. Literally no takers at all, by appearances. I'm sure RW Foundations would be vastly-further along today if someone (even just one complete beginner; b/c it would've kept me motivated) had been working closely with me on it for say, a couple years now. Eventually, I just got burnt out by the discouragement + the pressures of full-time student life (3rd degree's -worth in a row, so far). BUT... I haven't abandoned the RW framework itself! Just the fruitless "C++ language-teaching" part. (Grommet won -- his 'muh_anything_but_C++' niggerpilling beat me in the end...) LOL. JK, no it didn't! :D Hopefully I can find the internal motivation and pick it all back up again soon ... -ish. :^)
Edited last time by Chobitsu on 06/14/2025 (Sat) 01:29:18.
>>39225 I wrote this right as the site went down and saved it local. >I don't make fun of C++ developers Making it clear. I'm not in any way doing this. I'm saying that it's too hard for me and I believe for most people this is true. I'm not capable of making progress with C++. Any other language is difficult enough. >Please note the paper is not serious I fully get that. I hope your endeavors are successful. I do think writing a new language is going to take a long time but, if it amuses you then that's all that matters. It's not a contest. I do think though that it will be really hard to write something from scratch. The reason I advocate for this or that is not so much cheerleader but that I hope people of better ability than me at this, not difficult, will pick a language that I think they will make rapid progress. I know this may sound stupid but it is exactly what I'm trying to convey. Of course I could be wrong. I don't know anything about D, maybe I should. I'll look it up. (I did look at it) ehhh, from what I read Nim might be better though I obviously am not qualified to say. >NIM, it was one of the languages I ran into before I settled for D, I liked what I saw and if I was looking for a system language it would be high up on my list. I don't think it would make a good embedded scripting type language

Message too long. Click here to view full text.

Hello, long story short, be very careful when renting anything in the cloud. I know it's obvious advice, but if you're not careful you can still get screwed. I accidentally spun up more than one VM with expensive GPUs and it burned an eye-watering amount of money. That incident killed all motivation I had to work on this project for a while. I had a big hole in my pocket and nothing to show for it :( I preordered a Strix Halo system with 128GB unified RAM. It has arrived. Today I made a container with ROCm & PyTorch and got a comfy UI working; it's really cool that you can finally do video generation locally with actually nice models. I'm having a lot of fun! It's really refreshing not being super limited by VRAM. It's really neat that in basically 5 years we went from only specialist research GPUs can run this in a lab to here is a $2000 consumer-grade PC that can do it (but slowly). So this has boosted my morale a lot. Currently I am attempting fine-tuning/training of a language model of a useful size. So not a meme quant or a useless tiny 1-2B. There is not a lot of info online about how to do this on the Strix Halo, so I'll happily share how to do it once I get it working for myself. We might be soon at the point where local AI is no longer read-only in practice. I'll be catching up on the posts I missed on /robowaifu/ and I hope you all had a good Thanksgiving.
>>39347 Thanks for your points here, Grommet. >>43095 Sorry to hear about your little setback, EnvelopingTwilight. But it sounds like you are back in the saddle again! :^) I hope this new system works out well for you, and that you'll make good progress with it. Cheers, Anon. :^) <---> Happy Thanksgiving, Anons.

Open file (2.28 MB 320x570 05_AI response.mp4)
Open file (4.77 MB 320x570 06_Gyro Test.mp4)
Open file (8.29 MB 320x570 07B_Spud functions.mp4)
Open file (1.06 MB 582x1446 Bodysuit.png)
SPUD Thread 2: Robowaifu Boogaloo Mechnomancer 11/19/2024 (Tue) 02:27:15 No.34445 [Reply] [Last]
This first post is to show the 5 big milestones in the development of SPUD, the Specially Programmed UwU Droid. You can see the old thread here: >>26306 The end goal of SPUD is to provide a fairly high-functioning robot platform at a relatively low cost (free code but a few bucks for 3d print files) that can be used for a variety of purposes such as promotional, educational or companionship. All AI used is hosted on local systems: no bowing to corporations any more than necessary, thank you. Various aspects of the code are/will be modular, meaning that adding a new voice command/expression/animation will be easy as making the file, naming it and placing it in the correct folder (no need to mess around with the base code unless you REALLY want to). While I'm researching more about bipedal walking I'll be making a companion for SPUD to ride on, so it might be a while before I return to the thread.
327 posts and 153 images omitted.
>>43086 LOL. A cute! :D
>>43086 Y'all are really out here trying fuck mouse cosplay BMO instead of talking to any woman ever, smh
BANNED TO THE BASEMENT DUNGEON!111
>>43090 Oh hi obvious troll. To answer your question, yes, and? @Chobitsu obvious troll
Open file (72.54 KB 960x1041 chadpepe.jpg)
>>43090 TFW the cute college chicks oogling me during the numerous exhibitions of my robits. I must science before I procreate. I might make a medabot-size walking robit body for our Samurai Pizza Cat. Erm, Samurai Pizza Mouse. Depends how bored I get and how severely I get snowed in this year.
>>43093 >I might make a medabot-size walking robit body for our Samurai Pizza Cat. Neat! That's about the size I envisioned for the initial prototype of dear Sumomo-chan (a bit smol'r, actually... ~45cm or so). >Medarot Heh, haven't watched that in years. I'll be doing so a bit during the holidays. Cheers, Mechnomancer. :^)

Visual Waifus Robowaifu Technician 09/15/2019 (Sun) 06:40:42 No.240 [Reply] [Last]
Thoughts on waifus which remain 2D but have their own dedicated hardware. This is more on the artistry side though ai is still involved. An example of an actual waifu product being the Gatebox.
gatebox.ai/sp/

My favorite example is Ritsu, she's a cute ai from assassination classroom who's body is a giant screen on wheels.
451 posts and 150 images omitted.
>>42893 In accord with @Kiwi's sensible admonition -- and since I'm already quite-familiar with this product's platform -- I've ordered a little wheeled vehicle * for transporting the ArUco Markers & QR codes around on surfaces, just in case any'non here wants to follow along with my doings for this project. The plan is to print little tracking markers to affix to it, and directing it to drive around on a surface "carrying" the holowaifu along with it (in other words, as an expedient stand-in for the "BallBot" conceptualization ITT). --- * It has a camera + sensors, differential 4-wheel drive (can spin in-place), is compact (~ 6" cubed), and runs on the UNO R3. It's currently just US$55 (for Black Friday). https://www.amazon.com/dp/B07KPZ8RSZ
Edited last time by Chobitsu on 11/28/2025 (Fri) 15:28:22.
>>43082 >I've ordered a little wheeled vehicle Wait, I thought we agreed that we didn't need a robot for this, just graffiti.
>>43084 Eheh, yea we did. But I still want the little waifu to be able to traipse about in my flat before long. I simply decided to pull the trigger on this while it was still a Black Friday deal. No one else need get this yet. And beside, I still need to work out the camera+clip setup before that phase as well (cf. >>43073 ).
>>43085 So you want to try this because you think it would be faster to implement than digitizing your surroundings and rendering a waifu into that?
>>43088 Well you put it like that, yes (though that wasn't my reasoning). At the moment at least: a) I'm rather confident I can do the camera+tracking of the Aruco/QR car with my current knowledge. I'll just need to make the time to assemble everything and write a bit of code to support that. b) I'm not confident in the same way about digitizing my surroundings (though I'm sure I can get a handle on it when I make time to focus on it). Unless I literally went into Blender or Maya and modeled them. In either case, the rendering of the waifu is pretty straightforward. Again, we'll start smol and grow big with her designs & details (as with everything else for this project).

Open file (81.05 KB 764x752 AI Thread v2.jpeg)
LLM & Chatbot General v2 GreerTech 05/30/2025 (Fri) 14:43:38 No.38824 [Reply]
Textual/Multimodal LLM & Chatbot General v2 Models: huggingface.co/ >How to bulk-download AI models from huggingface.co? ( >>25962, >>25986 ) Speech >>199 Vision >>97 Previous thread >>250 Looking for something "politically-incorrect" in a smol, offline model? Well Anon has just the thing for you >>38721 Lemon Cookie Project >>37980 Non-LLM chatbots >>35589
40 posts and 5 images omitted.
>>41860 I can offer some insights. - having powerful hardware will improve quality immensely, but you can get a lower form of this up now with smaller models. - It will have context limit challenges which will need to be overcome with smart uses of tokens and how you store memories, but you can have a functioning thing as you describe, but detailed memories will eat into this heavily. having different ranked memory tiers and clearing lower ones and a mix of other clever ideas can improve all of these issues, at this stage it's just a matter of having a "lower resolution" AI companion, you could probably later update your methods as tech advances, and greater hardware means greater resolution. - I would suggest using multiple models to parse and make your AI companion smarter and not stuck into the patterns and paths that each models holds close to and deviates towards. to keep it simple, load one model, think for a bit, switch models, think a bit, especially with current limitations I would let a large chunk of time when the companion is by itself computing, to go over it's past and it's token database and refine it and have discussions and debates with itself to self-improve and refine itself. - I would have these personally as modes which you switch from her active life and talking to you, and her maintenance/sleep mode where she improves her database. - I will use sillytavern just as the idea vessel here, as I am used to it but I have not done this work myself properly since I'm busy with life. . . . use something like the memory and world lore books to store memories and events, they can each have a comprehensive recording into essentially "quants" of the lore books, where your chat history is fully recorded as non-quanted, then various levels of condensing and sorting out less important info/tokens, then your companion will think for each task and memory which quant of each lore book is suitable keeping in mind limitations hardware and current state of LLMs. - basically it will have a large database which it will parse and read through similar to how you will have it load models one at a time to use then switching to another, it will load different sets of the full database at a time to parse it. - You do the usual things you would expect, writing the personalities, creating the framework of the database, then you just have it use auto-mode similar to how sillytavern has group chats with different personality card as the other character, which is sort of her maintenance/ recursive improvement mode, again, multiple different reasoning/COT models being swapped through will be ideal here specifically.

Message too long. Click here to view full text.

The good news here is it's possible on local, and the bulk of the work will be in maintenance mode when you are not interacting with her, but for it to be good it will be very slow, but this will be when you are sleeping or away. When you are chatting, you will simply have to accept lower quality speech to you to make it run at a reasonable tokens/second generation, but pulled from the refined database which she created during her past maintenance phase where she runs a stronger model at an abysmally slow tokens per second/minute rate for precision.
Open file (76.13 KB 286x176 ClipboardImage.png)
Well, i was thinking about this for a long time, and i came to think that its actually possible to use a LLM with an LBM at the same time with a complex mecanism in an android for less that 3k, all in one, and even making it be self-aware if you make an especial LLM. using something similar to the organization of the brain itself you can emulate the way a human being acts, talks, imagine things, have complex thoughts, its central nervous system, making it esencially think about itself as a human being. Im currently developing it by myself using something more in the way of a gladOS, just for fun and money issues, but i would like to go for a more elbaorate build. wdyt?
>>43066 Good enthusiasm, you should put that enthusiasm into learning more. LLM and LBM are already used together. LLM do not seem capable of being self aware, though that's something to hash out in the aforementioned LLM/AI thread. >Emulating the human brain There's heaps of research on this topic over the course of many years. Please read what others have achieved to better understand the problem space. >wdyt I'd work on your grammar first. Then learn more about how various AI mechanisms actually work. You have potential, please do the work and read to better understand what you're talking about, then come back and contribute.

Open file (87.37 KB 800x1106 recruitment_1.jpeg)
Open file (110.19 KB 1024x1378 recruitment_2.jpeg)
Robowaifu Propaganda and Recruitment Thread 3: Now In 3D! GreerTech 09/16/2025 (Tue) 01:38:16 No.41674 [Reply] [Last]
Attention artists, graphic designers, marketers, social media personalities, writers, and poasters! Your skills will be needed! The task of building and designing a robowaifu is a herculean quest. As great as this community is, /robowaifu/ always needs more talent. We also need to spread the very idea of robowaifus to the masses. Luckily for us there are several communities on the internet that we could find new recruits or allies to help us build our waifus: >MGTOW - These guys know all about the legal pitfalls of marriage and the dangers of feminism. There is already a lot of talk about sex robots in MGTOW communities. It shouldn't be a hard sell to get them to come here. <However, some of these guys would rather spend all their time bitching on the internet about "MUH WOMENZ" than actually getting a hobby other than lifting heavy objects and putting them down again. MGTOW is literally Feminist Separatism for males. >Incels - Guys that can't get laid. The opportunity for love and companionship should be enough to bring some of these guys over. <However, we need to be careful when recruiting from some of their communities, since most of them are defeatists that balk at an actual solution, and they may be compromised by spies and derailers, both governmental and NGO/individual. We don't want to attract negative attention. >Monster girls/nekomimi/HMOAF/mlpol - The only way these guys are going to be able to have their harpy/elf/goblin/anthro/pony/whatever gf is with a robowaifu. Many have an interest in seeing us succeed. <However, there exists a very wide variety of communities under this umbrella, and there is a notable overlap between communities who would want robowaifus and communities that are morally compromised, such as furries, so care should be taken when looking into them. Romanticists and waifu enthusiasts have a tendency to congregate since they all want/create the same type of content, so looking for those subgroups would be the most efficient path. >Otakus - Many men in these communities want to see their waifu/favorite character come to life, which will realistically only happen with robowaifus. <However, many of those communities are drowning in the LGBT alphabet soup and Covid Tourists. Special care should be taken when looking into them. >Male STEM students - Generally these guys aren't going to get laid until after they have established themselves. A robowaifu could really help them.

Message too long. Click here to view full text.

Edited last time by Chobitsu on 09/16/2025 (Tue) 02:33:18.
104 posts and 55 images omitted.
People think that the purpose of public debate is to change your enemies mind, but that isn't the case. The point of public and large-scale debate to make your enemy look foolish at best, and downright evil at worse. That's why leftists hated Charlie Kirk to the point of murder. He made them look foolish constantly, up to his last breath.
>>42962 POTD Based and Wisdom-pilled, GreerTech. Cheers. :^)
Open file (77.00 KB 1024x1024 robowaifusymbol.jpeg)
I recently learned how to do favicons on HTML, so I added a little chibi Galatea to the robowaifu link page https://robowaifumuseum.neocities.org/robowaifuboards
>>42977 A cute! Nice work, Anon. GG. :^)

Report/Delete/Moderation Forms
Delete
Report