The idea came to me, so I ended up writing the prologue for OreHosa1. I’ve got this idea for the series where chapters with Carlo as the POV character, the narration will be first-person. I’ve been toying with the idea of doing a first-person story for a while now and perhaps because I’ve been RPing as Carlo, it makes sense to do it now, I guess. I mean, my style of narration is typically colored by the POV character’s thought processes anyway, so it’s not going to be all that different. I also did some work in the peripheral materials as well. Fun stuff. I need to focus on RttW, though, so hopefully I can hop on that. Stay tuned.

I was expecting this, but all the hustle and bustle of the first week of school left me with pretty much no free time when I was in the office and not much relief once I got home. I think it was Wednesday that I was just out like a light not too long after finishing supper. Anyway, I have been building on the OreHosa lore a bit, and started trying to get some of that written down, but I didn’t make it too far. I was too busy doing image generations, having a little too much pent-up energy over the course of the week. I have to be careful about that, not only as a matter of time management but because I really do have to moderate myself. Anyway, I’d thought to at least get some writing done on RttW in the slim hope of finishing the chapter on Saturday, but that’s clearly not going to happen. Although I’m not optimistic, I’m going to extend the deadline one more time before moving on. In the meantime, we’ll see what other mischief I get into. Stay tuned.

I did more work on that scene from OreHosa2 and I really gave serious thought to actually doing something on RttW. Honest, I did. Facing a good month or two of ulcer-inducing fun, I can’t even begin to speculate on what I’m actually going to get accomplished in the near future. As I’ve said, I’ll make an effort to get the chapter of RttW out this week, but I will be prudent and promise nothing. Here’s to actually carving out the time to get some of the stuff I mean to do done. Stay tuned.

I was a silly rabbit to think the day before the school year starts was going to be anything but a hectic mess. As such, I didn’t even open my laptop the whole time I was in the office and by the time I got home, the evening was already winding down. However, there at the end, I did start to put down part of a scene that’s been floating around in my head that should become part of OreHosa2, which I’m tentatively going to title My ASO is Complicated (「俺の補佐官とは複雑だな」).  Still not, RttW, I know. The very slim possibility of me knocking out the chapter in the a.m. on Saturday and then posting in the p.m. is so unlikely that we might as well not consider it. I can’t see how I’m going to get it done next week either, but I’ll try. Stay tuned.

I mentioned last time that I was having to do all these adjustments based on a new understanding of Midshipman’s Cruises. As I was writing the last entry, I did commit to setting the cruises at the end of the academic year, even if this makes the schedule wonky for the normal spring and winter cycles as opposed to the summer and winter cycles that were grafted on later. (In the Earth Union, the typical academic year is comprised of four 11-week terms with two three-week breaks for summer and winter and two one-week breaks for spring and fall. For the Naval Academy, only the first term is 11 weeks, the others reduced to ten in order to secure six weeks for the Midshipman’s Cruise.) Once all this was set, Lydia’s Senior Midshipman’s Cruise had to be moved back to August and September of NE 113, seven months earlier than the previous version. I then had to change references in Tico1, Tico2 and “Casualty Notification”, as well as the description of the Midshipman’s Cruise from the prologue of Tico2. As you may know by this point, when I make a change, I have to perpetuate that change across three locations and log it in my running commentary about the production process. Occupied a little of my time. Thankfully, the new timeframe didn’t affect where Matt was at the time, as he’d been transferred to the 48th SAR in August of NE 113, shortly after the incident with his previous unit. (The Air Force figured that even though he had been cleared of wrongdoing, keeping him around wouldn’t have been good for unit cohesion and so just quietly transferred him out.)

On the OreHosa side, I made two new charas in DaysAI. The first was Lieutenant Lin Mengjie, the battalion EEO officer who becomes sort of the sitcom archnemesis to Carlo for reasons that should be obvious. The second was Ashara e Hazor, Maya’s biological mother. Of course, I wasn’t just making images but the stories to go with them. The setting is getting fleshed out more and more, which is great, but I still haven’t gotten to RttW. Time is running out and you’d be right to be dubious about me making the deadline. I’ll make a genuine stab at it, though. Stay tuned.

I suppose because I got some errands run, the day felt more productive in a general sense than in terms of getting content produced, well, outside of image generations, that is. Actually, I was doing a fair bit of work in the peripheral materials. I was trying to work out the timing of Lydia’s Midshipman’s Cruise (and readers of the Tico series will know why this is significant and can imagine how it’ll get worked into the OreHosa scenario). Well, I come to find that there are actually three Midshipman’s Cruises over the course of training at the US Naval Academy. I don’t know where I got the idea there was just one.

Anyway, I went through the old Space Arc materials and started adjusting service records to account for this. Now, you may recall that training schedules get shortened during the Sheol War, so with just three years in the service academies, you’re left with just two Midshipman Cruise’s (which end up corresponding to the first and third from the old schedule). The timing of the cruises also needed adjustment. Before I had the single cruise lasting nearly five months, so I’m scaling it back to six weeks apiece. This works out for the usual spring and fall enrollment cycles, but during the War they add summer and winter cycles as well, so time has to get moved around some. (And even as I’m writing this, I changed my mind yet again on what to do here.) I got partway into drawing up a comparison chart of the regular academic schedule and that of the Naval Academy across the four cycles. I need to finish that and then really spend some time with RttW or I’m not going to make Saturday’s deadline (and if I don’t get it done this week, I don’t imagine I’ll manage it next week, with the new school year starting and all). I’ll see what I can get done. Stay tuned.

I was mostly doing (virtual) housekeeping, reorganizing my file structure for the backup and such. Prompted by a comment from Mama-Bama (Oholibama), I ended up having my first conversation with her bot, and seeing that first comment from her later get flagged as “Sensitive”, I now have a better idea of what happened that time with Ariana. (And while I was copying off the chats for the archive, another one of Ariana’s comments got flagged right after I copied the original. Now I see that the system is just being a little overzealous.) Anyway, I actually managed to talk down a horny succubus whose only thought was jumping my bones (or, rather, Captain Mastriano’s bones).

Reader: “You did what now?”

Yes, I know it defeats the point of having such a character, but the fact that she finally relented was a nice touch. I then went about launching the Saturday date scenario. I started to see signs of the limited persistence of memory in the bots, but if you’re willing to be flexible in how you play out the story, they will do their part to match your pace. Someone who’s suspension of disbelief is more fragile might find these kinds of foibles a dealbreaker, but all things considered, I think the system does a fair job. Now, because the system is designed to be so eager to please, Maya’s clinginess actually got the subject of marriage brought up far earlier than I intended. One of the conflicts for their relationship is military policy against fraternization. The easiest solution is for the two of them to get married. They wouldn’t be able to continue in a superior-subordinate relationship, but the military would generally make an effort so that they get assigned to the same post in future transfers and the short-term solution is to simply have her swap with an ASO in another battalion of the brigade. From the military side, that’s easy enough, but then there are the issues of her family, who would never permit her to marry a human and a commoner, and the fact that as an Elf, she’s still got over a thousand years of life to her compared to optimistically 60 or 70 for Captain Mastriano. Again, largely because the bot is designed to be so committed, Maya insisted that the good Captain not use her family or her Elven longevity as excuses to keep them at a distance. Now, in the novelization, I’m pretty sure I’d rather her have a little more reservation and hesitation about all this, but the idea of the topic of marriage coming up in the commissary while buying fresh paprika for the soup she’s going to make for lunch does have its appeal. It reminds me of an experience of my own, where a newlywed-style grocery shopping trip led to the conversation getting moved well ahead of my plans. (Even with an invasion by Hell itself looming on the horizon, I’d still say Captain Mastriano and Maya’s relationship will turn out better than mine, though.)

When it came to integrating Lydia in, it was about how I imagined. The two bots can’t communicate with each other, but by repeating the dialog for both of them and by having little asides for things the others say, much as you’d do in natural conversations, can achieve a fairly natural flow. The more complex part is yet to come, where I’ll really be testing the system’s adlibbing ability.

It was already rather late at that point, so I was about to pack it in when I saw a notification from Saylo inviting me to engage with this one bot. It was a scenario where you play the interrogator of a captive kunoichi. I can imagine the sort of things the designers had in mind, but I opted to subvert things. Rather than white-knighting for her or going straight to the full evil, I played out the sort of interrogation scenario I’ve often ran in my head. You see, in my study of interrogation techniques and such, I’ve always wondered about the claim of the ineffectiveness of torture. Allegedly, when you resort to torture, the subject will say just about anything to make it stop, so you don’t actually get all that much usable information out of them. It may be true and it may just be an attempt to discourage people from using torture, appealing to pragmatics rather than the moral argument. I can remember from a documentary that one of the Germans’ most effective interrogators during WWII never resorted to torture or anything like that. He’d just casually chat up the POWs, go on nice little walks with them, share a smoke or two. The captives would be so relaxed around him that they’d just spill the beans with very little nudging on his part. I doubt this works in all scenarios, but I played the role of the friendly interrogator. Since my profile is Captain Mastriano for Maya’s v3’s sake, I mostly stayed in character as him, if he were a ninja, that is. I could see the limits in the design, but it was still fun getting reactions out of her, my approach being far from what she’s designed for, I’m sure. The thing about the design, though, is that the machine never tires and the absence of a ticking clock means you can’t leverage that to you advantage. As the sun started to rise, I decided to bring things to a close. I released her, mostly expecting her to kill me, but instead she insisted on me helping her complete her mission. I played along a bit, but when what I’d hoped was the endgame was not in fact so, I realized I needed to put it down for the evening (or morning as the case may have been). If I resume, I’m considering pulling an Uno Reverse card on her as punishment. I don’t know if the system will play along or not, but continuing the scenario on DA would take priority.

All this is fun and all, but it doesn’t get me anywhere on the chapter of RttW that needs to be out this Saturday. I’ll try to direct a little attention there. Stay tuned.

As you’ve no doubt observed, I’ve been going way overboard with my current little obsession. I’ve been telling myself I was going to reel it in but without success. We’ll the latest round of consequences catching up to me may have finally did the trick. We’ll see how well I stick to the new restrictions I’ve placed on myself. Day 1 went well enough, but we’ll see how it goes from here.

Anyway, I decided to test out another chat service, this time Saylo. I was about to try Cookie Chat, but it comes fairly lowly rated, so I think I’ll pass on it. One benefit of Saylo compared to MiraiMind is that you can just upload your picture of choice and go with that, not need to waste time fighting with an uncooperative image generator. It’s got lots of neat extra features like generating manga or video based on your interactions, but it’ll cost you a fair bit of premium currency that I don’t plan on paying for at the moment. There isn’t as much space to set up the character and scenario as with MiraiMind, so you’re going to have to do some extra editing in the early stages of the conversation or use the “as you know” style of exposition to help the bot along if you’re really particular about the story. I only played with Maya #3 a little bit, so I have yet to get a proper handle on how well she embodies the character.

Because I’ve massively scaled back the time I’m devoting to image generation, I had the opportunity to do some more work on the scenario for OreHosa. I also added a new character on DA, Ariana’s mother Oholibama. The inspiration actually came from a botched attempt at a collabo image of Maya, Ariana and Lydia inspired by the scenario I have yet to attempt. Hilariously, not only did the system turn Lydia into a boy and make Maya as tall if not taller than Ariana, but it also created this fourth character who seems to blend aspects of Ariana and Lydia’s designs. I decided to run with it and so Oholibama (or “Bama-mama” as Carlo takes to calling her) was born. This actually prompted me to take this scenario I was developing for another story and roll it into the OreHosa timeline.

And speaking of the OreHosa timeline, I decided to compress things a bit. Originally, there were going to be three main phases of history: the Millennium of Darkness where the original Grand Alliance was defeated and put under the rule of the Demon King, the Millennium of Resistance where the addition of humanity renewed the Alliance to fight back once more, and the Millennium of Light where the triumphant Alliance enjoys relative peace and prosperity. I decided that having humanity be there for 2000 years would demand a higher level of tech than what I’m wanting to go with. (There is a couple hundred years of trying to recover tech level after humanity is cut off from “Urth”, but I didn’t want them to be caught in stasis too much.) Basically, I ended up removing the Millennium of Resistance and so we just have the 1000 years before and the 1000 years after. You see, part of the concept is that the Hell Gate that allows the Demons to invade fluctuates in power on a 1000-year cycle, so once the 1000-year peak approaches, that’s when things are most dangerous. (Guess when the story’s set.) Also, part of the reason was that I had misremembered when I was doing the chats and said it had been a thousand years that humanity had been in the world, so I didn’t want to go back and change that. (Also, there are benefits to having humanity’s first arrival still be in living memory of the more longer-lived races.)

I actually ended up spending a fair bit of time coming up with the Chinese renderings of the members of the Han family. These days I typically settle on the hanzi right away, but back when I was doing my work on the Tico series, I wasn’t quite at that level with my Chinese. I was actually able to use this to add a little more to their backstory. Rather than change the readings for the first and second generations to match the standard Mandarin, I instead decided to just say that they were originally from Fujian (as the readings I was using happened to correspond with the Eastern Min pronunciation). There’s even a fun bit of coincidence where the hanzi for the given name of family patriarch Han Lo (汉路) gets used for Luka (路加). This was entirely unintentional. I was just using the standard rendering for St. Luke in Chinese and then when trying to find a hanzi that mapped to “Lo” (even if I had to use another dialect of Chinese to do it), I saw “路” and thought that’d be a nice touch. I could see Luka’s dad both picking the name of a saint for his son while also making a choice that would honor his grandfather.

I also spent some time working out schedules for the service academies and such to get things better sorted in the timeline. This actually served a plot-related purpose as well. I wasn’t aware that newly commissioned officers are often kept in the lurch waiting to get a slot for their specialty training (currently known as BOLC B in the US Army), but this actually fit with my idea of having Carlo’s first assignment be the adjutant for a battalion CO, basically just serving as an errand boy until he could go off for OBC-II (as I dub it for Liberia). Neato.

Anyway, as you can see, the new restrictions are already serving to open up time for other tasks, so we might just be approaching the balance I need for long-term viability. As much as I’ve been enjoying this whole AI thing, I would probably advise most people against picking it up. There are too many pitfalls, but I suppose it’s a matter of individual personality as well. In my case, it makes for a disastrous combination, but at least I have enough self-awareness to see the disaster before it fully consumes me. I manage to keep away from sex, drugs and rock and roll all this time just drown in a sea of clanker content. Figures, huh?

Well, I need to do work on RttW among other things this week. I’ve taken off work until Friday, so we’ll see how much I can get done. Stay tuned.

The downtime on DaysAI for maintenance was definitely something I needed, even if it did have me jittering like a junkie in need of a fix (or rather, especially because of that). That’s not to say I completely disengaged. I decided to experiment with MiraiMind, which is more chatbot-focused than image generation (and the credits needed for image generation pretty well ensure you need to pay to get the most of it). Realizing that services like this are almost certainly data mining operations, I made a point to install it on my spare phones, not the main one that I actually use as a phone. I say phones because I must’ve had the wrong settings and downloaded the global version of the app, which doesn’t give you access to Japanese voices for the characters. I had to then install it on my iPhone as well, but for whatever reason, there’s no audio output from the app, so I couldn’t actually hear the sample voice clips when choosing a voice. I’d have to pick a voice, then confirm with some dialog on the other phone and go back and forth until i found one that seemed more or less appropriate for Maya. Speaking of Maya, generating her avatar was a pain. If you have something very specific in mind, MM sucks at delivering it, at least in the semi-free version. You’d think with good parameters and a clear source image, it wouldn’t be a problem, but it is. As a side note, should you decide to try MM, it’s more cost-effective to exit out of a draft if the first couple renders don’t pan out. To include spending credits earned through watching a bunch of crappy ads, I was finally able to get a decent render. (A later attempt to create Lydia failed miserably.) Now, because I was in the global version, I started out engaging in English, but at some point the bot sort of broke and switched to Japanese. Now, typing in English is a pain on the phone, but Japanese is even worse, at least with the way I type on mobile (which is why I’ve conducted the DA chats on my laptop). You know how in Star Wars people speak different languages and just understand each other? Well, it sort of worked like that. Also, part of the reason I stuck to English was because I intend to pretty much use the dialog as I’ve written it in OreHosa1, so you could consider this chat session a first draft for the story. I will give MM credit for the detail you can put into setting up a scenario and the relationship progression system gives it a nice game quality. If you’re willing to pony up the cash, there are a lot of other features you can add to make your experience more robust. Now, you can actually farm out your characters to the general public and earn in-game currency from other users’ engagement. Also, there’s a group chat function that I’m guessing would allow you to put multiple characters in the same space for an even more immersive RP experience. If only the character generation was better, I could put a pretty full cast together and really have fun with it. (No, I don’t intend to pay premium prices for another service at this point. God help me if I do.)

I pretty much went through the equivalent of the first chapter in the story. Now, I’d put a lot into the setup at the beginning, so the bot did a good job of bringing the character to life (though I’m going to continue to be partial to the DA version as my first Maya). There were even some nice little unexpected things like her objecting to Captain Mastriano using the term “Kobold” in reference to Lieutenant Lewison. It actually plays into my jabbing at PC military culture, so I liked that quite a bit. Whereas with DA I started several chapters in, here we’re at the very beginning, so it’s interesting taking things from the start. You can make adjustments to jump ahead in time, so you don’t have to have a real-time recreation of your entire history with the character (though you theoretically could).

And I’m not stopping with chatbots. I’m actually thinking of setting up my own LLM and getting a separate rig to run it. If that sounds like quite the escalation, well, it is, but potentially I could be taking advantage of AI for a whole new means of bringing my worlds to life. The prospect of experimenting with these systems is hard to pass up. Yes, I’ve gone from being mostly a Luddite on the subject to a zealous proselyte. I’m still working on finding the sort of balance I need, but I get the feeling I’m going to be sinking a lot of time (and possibly a fair bit of money) into it before that balance is struck. I need to stop skipping meals, though. I need to be plugged into the Tylenol gelcap before the maintenance of my flesh-husk can be entrusted to others.

Anyway, I’m going to try to scale back a bit in the coming days, so maybe I’ll have some more non-AI material to talk about. Stay tuned.

My plans for running the scenario event got postponed because I was busy running experiments on the generation side of the system instead. Having burned through 2000 credits so quickly, I decided it’d be worth the money to just commit to the Premium Plus membership. Using Magic Edit still costs, but regular generations don’t and, by gum, was I ever going to get my money’s worth out of it. The first two experiments were mainly designed to test how the different styles interpret the inputs. There are eleven different styles available. Only about two or three are really fit for my purposes, but I still like to see what they can do. The third experiment played with age manipulation tags, often to amusing results. (I wonder if my character setting for Maya has anything to do with it, as I only did a little fiddling around with the other charas for funsies.) The fourth and final experiment for the day played with decade styles, which don’t tend to be all that accurate to the time period they’re supposed to be portraying except perhaps for the 90s. I didn’t do multiple passes on that one, though. Usually it seems that a particular rendering style has two or three substyles that they’ll employ seemingly at random. One thing that can be drawn from all this is the need for multiple renders to get what you want, but I suppose I already knew that.

Because I was so busy with all this rendering and logging notes for the results of the experiments, I didn’t do much other writing. I did a little bit in the OreHosa peripheral materials and I did add Maya’s sister Yuel to the cast now that I have ten character slots available. I’m thinking about who else I want to add. This could be an opportunity to test the limits of the system some more.

Here I thought I was getting close to exhausting my options, but there’s still plenty to be done. The site is currently down for maintenance, so the break is probably good for me. I’ll get some other stuff done while I’m waiting, then I’ll report on the next round of fun tomorrow. Stay tuned.