Home

The wiki documents my findings and observations attempting to condense World Info (WI) entries down as compact as possible, down to the last character. This is a fork of the Futureman format, but has deviated away from it more and more each day.

What do you need?

• This format, like Futureman, is designed to work with EWIJSON.
  • New here? What the heck is EWIJSON?! It's a script that provide more control over how AID uses WIs. Normally, AID puts a triggered WI up at the very top (hidden to viewer), but EWI lets you place it anywhere. Because of distance weakening (the higher up something is, the weaker its importance to the AI's writing direction), combined with concepts that are inherently weak already (unusual fantasy races, weird behaviors, concepts the AI doesn't understand well), EWI is a useful tool to move these down lower to counter this problem.
• Time. This format is tedious and time consuming. You'll need to have a token viewer handy, like this one. There are others out there. Ask around on the discord for other options.

Strengths and Weaknesses

• It's primary strength, as the name suggests, is reducing WIs to as few characters as possible. This allows more characters to be reserved for the actual story content instead, and/or being able to trigger more WIs without overwhelming the memory.
• This format does not make any promises on being the most accurate or strongest of the formats. There is some expectation that you will need to occasionally reroll an output, but not so much as to frustrate the player into giving up on a concept.
• This format normally does not concern itself with an overbearing amount of entity definition. It's more about pointing the AI in the right direction and letting it do its thing.
• Due to its nature (explained later), this format is unlikely to work well on anything other than dragon. I do not use griffin enough to comment on how well it compares to other formats.
• Neither a strength nor a weakness, but full disclaimer: I primarily play in 3rd person mode, and only using story input (as opposed to Do or Say input), and with a 1.1 randomness. My bread and butter genre is high fantasy medieval in a world with a wide variety of colorful races.

Character example

Best I just teach by example, and explain why things were done the way they were. This character is defined with 3 WIs. Here is the first of three placed at the p=1 position:

< Cheeps♀AvianPink feathers>

• First, the encapsulation. Those familiar with futureman may already be aware of << >>>> encapsulation.
  • Futureman encapsulation is more resistant to the WI format leaking. Most of the time I do not encounter leaking. When I did, it was typically when I was breaking the fourth wall and prompting the AI to try and test out a WI for accuracy.
  • The odds of leaking increasing the more WIs you have currently triggered, overwhelming the content. This can be countered with the [f] filter argument.
  • More niche, I've seen the format leak when talking to characters whom intentionally have bad grammar for whatever reason.
  • Monky, author of futureman, states < > is the second best encapsulation according to his testing. It should be noted, however, there are a wide variety of tests and scenarios to account for, and what reflects in one set of variables may not reflect in another. In my experience, < > has suited me well. This format is all about shaving off every last little character, and little by little it adds up.
• Next, the leading space before the name. While this format hacks off leading spaces left 'n' right, special care is given for the subject noun. We'd like an exact token match for how it will most often be seen in content. Predicting that it will most likely be used mid-sentence, we leave the leading space. But there are exceptions, explained later.
• The name itself. If you have the luxury of picking any name you'd like, try to pick one that is token-friendly. Here are some thoughts on this:
  • If you use an irl name that's somewhat common, there's a good chance it may be a single token, and the corpus may already include gender bias to it. But it may also include some other undesirable biases, you never know. Single token names are very strong with keeping the AI's facts lined up.
  • Single token names-that-aren't-names seem to work fairly well, especially for animals. For example Lumin or Snow.
    • Names that are self descriptive of a trait (for example Snow having white fur) helps a bit, too.
  • When it comes to multi-token names, I aim for two tokens if possible. But what's more important is token length. The more open to interpretation a fragmented token is, the worse.
    • For example if a token splits up in such a way that one of the tokens is I or He or some other word, the AI could read this the wrong way.
    • Single-letter tokens may sometimes be misunderstood as being typos.
  • 3+ letter tokens (that aren't confusing words) are rather safe. In this example, Cheeps is Che + eps and there is practically no room for confusion.
  • Even if you do everything "perfectly", there's a chance it may still mangle a name due to built-in repeat penalty, depending on how frequently it has been written.
• The gender symbol, attached directly to the name, no space. After using gender symbols for a few weeks, I've nothing but good things to say about them. But, some notes:
  • Community consensus seems to be that the female symbol works better than the male symbol. Personally, I've only really encountered the AI getting female characters' gender mixed up (especially when using fantasy races that are male biased, such as more bestial creatures). I'm confident the symbol method has shown a marked improvement at locking things in correctly.
  • As for males, it's been said that the symbol is weaker than words. Personally, I still use the symbol so shave off a few characters, and the AI seeing some pattern consistency between characters may help.
    • If your cast is overwhelmingly male, you could consider not using the symbol if you find it's not doing you any favors.
  • Non-binary symbols also work very well. If it's a herm you're after, ⚥ is all you need.
• Next, the race is defined. No leading space, which will be explained for the race WI later.
• Next the primary integument color. Yes, color! Everyone's favorite and most frustrating topic for AID to mess up. With EWI, color issues are more or less solved and only mess up about as much as AID messes up even the most perfectly executed things due to pure randomness. There are some rules to follow:
  • This format really goes out of its way to make sure there's never a leading space before the color, AND
  • That all colors should be a single token. Why is pink written with a capital P, Pink? Because only this form of the word is a single token, not the lowercase form. This is just one of those case-by-case things you need to check in the token viewer.
    • If given multiple choices of single token colors, the lowercase form is preferable since this is what would actually be written in a sentence most of the time.
  • The color can be either before or after the subject, and there may be reasons, explained later, why you'd flip them around. Normally, having it before it stronger.
• Finally, the integument itself, which is feathers for this character. If feather could have been used, or without a leading space, it would have been used instead. But our top priority is finding a form of the word that is single token, and in this case, it was feathers with a leading space.

Next is WI 2 of 3, defined at the p=5 slot.

< Riskit ≡ scatterbrainGreeneyesnicebeak scatterbrain slender BreastSmall& necklaceofbell&She servant povertyin Wicklow>

• Encapsulation and already explained, so moving onto the Triple Bar ≡. We borrow this from the Cat format and give it a leading space because the leading space version is only 1 token, and 2 tokens without.
  • This symbol means identical to
  • Whereas futureman/caveman is more about a devolved form of prose, this format is more about listing out attributes in a particular order, only using grammatical words to aid when tests are faltering, as you'll see in later examples.
• The first attribute should be whatever is most important to you. The closer the attribute is to the subject noun, the more weight it will get. In this case, we wanted this character to be portrayed as comedic relief: scatterbrain
  • Through testing with the token viewer, scatter needs a leading space to remain a single token, but brain does not.
• Like before, the only way to get the color, without a leading space, into a single token was to use its capitalized form.
• eye is written instead of eyes. Shaving off every character we can, we always use shorter variants of words if we can get away with it, drawing on the strength of dragon's understand to rewrite this properly when actually used.
  • Sometimes you need eyes, plural, depending on what the token viewer shows you.
• beakgray, the color is behind the noun this time so that the AI won't accidentally think to associate it with the eyes instead.
  • Note: gray is used instead of grey as it is supposedly a more common token.
• This character is a real featherweight. Skinny, thin, slim, what have you. The word slender was chosen during the testing process as it appeared to be the strongest, a topic that'll be discussed in the testing section later.
• BreastSmall. No this doc is not meant to be NSFW orientated, but this example was left here to talk about the subject of bias. Female characters whom find themselves in even the slightest level adult situations are often depicted as having big breasts. You can thank the internet for that. This bias is so strong that traditional WIs seem to go ignored trying to fight it. Only with EWI, allowing the WI to reduce its distance penalty was reliable with countering it.
  • In the interest of single token words, Breast non-plural, leading space was chosen, and Small capitalized allows it to be mashed onto the back without fragmentation, unlike small. I won't keep explaining this every example. You can assume capitalization and plural variants have all to do with this.