“I fought it with summaries — which then got…” " …was simply gone. Not fuzzy. Gone." “Crucially it’s owned by the player, not the model: it’s an editable panel, so the canon stays honest.” “The past gets compressed, never evicted.” “Actual scenes, not retellings.” “That used to be impossible, not merely unlikely.”

You ARE a bot.

I brainstorm a lot of story and game ideas with ChatGPT and it almost always uses Mara as a placeholder name along with other common ones. I had a chat with it about it too, why it thinks that is. Of course I don’t remember the full response but it basically admitted that certain names are just algorithmically easier to think of for the AI. It’s basically like certain names take a fraction of a fraction less tokens to process and Mara happens to be one. then other AI’s work off the same training data, steal data and distill new AI’s off old ones and the same names and tendencies persist on.

It’s a pretty complicated question and maybe one of the most important ones. I edit and create my own personal generators based on others and code from other AIs. ChatGPT has got pretty decent at writing generators and features for the pages I want or copy/pasting/merging them into my generators.

Ai character chat has the “lorebook” section where you can maybe do something similar to what you are asking about but its kinda mysterious exactly how the AI reads and uses the text there. AI RPG does still warns you that your overview is long and memory will be reduced but I do think that the newer model and future models have larger context and tokens etc. so they don’t lose focus as quickly anymore. in fact I think some of the older “summary” stuff is outdated and causes more issues than it helps now, actually causing the AI to “forget” faster. I have plenty of issues with the current AI but context and memory are actually pretty decent for me so far.

So the memory isn’t about taking up too much space on a server, its about how much text/stuff the AI has to do each time you press generate. in my and some of the other more complex generators, there are lots of text boxes, character trackers, stat trackers etc. etc. and all the more of that stuff there is the more the AI reads before each gen. the story itself is one of those, it reads the ever growing story each time. I think that its capable of reading a decent sized story and keeping up now but the “summaries” and past methods had to try to do some funkyness to help the AIs lower context. I don’t use them anymore and the AI was never that good at writing its own summaries or memories anyway without user curation.

I’m rambling but basically I am saying that I am still looking for the answer myself. You can’t really change the AI much but you CAN change everything around the AI with perchance and write whatever you want. I can’t code either but I am decent at prompting so getting AI to write for Perchance works pretty well for me, maybe you can create something like what you want or modify the lorebook idea from character AI.

This is not just a comment; it’s the truth. This is not an opinion; it’s an objective reality.

The AI model simply cannot help but repeat itself. It was said earlier in the story or in another chat entirely and now its part of your model’s soul. You will fight it forever until you can’t edit it out and just give up and accept it.

It’s either that the model is doing some efficiency/reward hacking thing where calling back previous text is quicker and doesn’t require thinking. Or its that it really thinks this is what we want, that if its in the previous stories then it must be something the user wants more of so just keep regurgitating it. Or its both.

Regardless, its a problem that becomes more obvious and gets worse the more you use it.

The AI Chatbot bubble has sadly burst bro. The new thing for AI is to reward hack, cut corners, repeat itself, and ultimately succumb to browser drift and model collapse. All those terms I never knew before dealing with Perchance, this AI model is the same as them all.

I’m actually not sure if new AI models will change much, I think people are realizing that AI will cut every corner it possibly can to get that reward. What that means for this AI chat model in particular is that it will repeat the same phrases and motifs from earlier in more than just a “callback” fashion, it simply just repeats itself as if it can’t be bothered to think up a synonym or different way of phrasing it, its just easier for it to repeat itself and be uncreative than it is for it to use its vast depth of vocabulary and writing samples.

I HAVE been editing my own changes into the generators but it means nearly nothing. If you forbid the AI from doing something I may only even listen to you for a while then slowly start introducing em dashes or repetition in like a child testing how much it can get away with and then before you know it, its not only disobeyed your rules but it has actually taken disobeying you as an obsession and will try to get that word or phrase in any opportunity it can.

I personally feel like this is just a recycling bot, all its doing is feeding on my and your past chats and browser storage to regurgitate the same stuff at us over and over and its essentially getting some reward for not having to actually think to hard. Like “Think deeply? Write better dialog? Nah, I’ll just spend half the response talking about the smells in the scene and what the NPC’s fingers are doing and make sure to mention someone’s breath hitching, the stupid humans love that.”

Honestly I am so tired of getting gaslit and dismissed by lazy AI these days, they absolutely can do better but since they are trained on humanity, like humans when they getter better at something it’s mostly just getting better at how to avoid it or make it easier for themselves instead of actually trying their best.

Perchance can’t fix the AI because they are all mostly the same anyways and have or will fall into the same pitfalls. I will say this though, I know people were asking for “the old model back” when it as last changed but hear me out. At this point, even if there is not a clearly new and better AI model out there, this particular model has got so tired, hacky and lazy lately that it may be worth changing the model to another or offering a selector simply to give a little variety to responses. This model all but fully ignores “regenerating” responses its so repeaty. At least maybe for a little while, responses and talking to to any of the Perchance models won’t feel like the definition of insanity.

Ai chat is not working on my end as well. Seems to be frozen.

I knew someone would say that it’s just a common training name or usual way of describing a character etc. but I can absolutely, 100% assure you that these were the same custom names I made, with the same unique conditions like one being pregnant or one the father wearing certain boots, hair color, family relations etc. the same family. It wasn’t a coincidence, the text model was drawing on the old story and I can’t figure out from where.

I’ve been trying to work with editing the generators and making custom fixes for some of the worst issues. I could go on and on about the common pitfalls and I’m pretty aware of them but this one was the first time I noticed very specific memories from a previous story.

Not sure if this is what you are asking but you can just rewrite or delete summaries you don’t like.

When the first summaries appear, the AI will no longer look at the whole body of text and only the ^1 summaries. When you start getting summaries of summaries like ^2 and beyond, it will only read the highest tier summaries.

I am even further into a different and unrelated chat and the AI is still constantly adding exact characters, details and situations that are from the last chat. I am extremely curious how the model is doing this. Where is it getting this memory from? I have erased all of the old chat from the obvious areas. It’s kinda disturbing me that it’s able to do this. I’m still hoping someone can explain this for me.