This is a linkpost for https://dkl9.net/essays/positive_english.html
This might be an interesting use of LLM rewrites: negative->positive rephrasing feels like something within GPT-4's capabilities, and it would let you quickly translate a large corpus to read & evaluate without putting in a huge amount of work to write a large varied corpus of Abs-E text yourself. (I dislike the current name 'Abs-E' and by analogy to E-Prime, suggest 'E⁺' - short for 'English-positive'.)
Took a first stab at just the positive rewrite last night: https://github.com/gwern/gwern.net/blob/master/build/text2epositive.py
A major issue is that GPT-4s want to rewrite into ChatGPTese and hypercorrect any 'error', even with instructions to preserve the style and a lot of examples showing style preservation. I greatly want to avoid ChatGPTese in my writing, so it leaking through anyway is a problem. Another LLM API might be better for this (Claude?) but I don't have tokens+scripts set up right this instant for alternatives.
That aside, I'm unimpressed right now with the generated rewrites. Working through various examples of negation is hard and yields ugly-sounding or too-strong assertions or I couldn't do it at all without cheating, and makes me think that often a negative assertion is the most informative (without being false) way to state something.* There are negatives that should be reworded to positive, but fewer than I was hoping beforehand. (For example, the comment about the LW2 AWS hack reads better when rewritten into an affirmative positive form, definitely.)
At best, this seems like something to integrate into a grammar/style checker and only occasionally suggest a rewrite. And of course, if you only occasionally rewrite some text, the value is much lower than if you were rewriting every other sentence.
I feel a bit more optimistic about up-goer-five rewrites at this point. Although I'm not sure where I would actually want to generate a lot of up-goer-five rewrites, come to think of it...
(A linter-style tool just flagging some text is also harder to integrate into my Emacs writing workflow: if it rewrites an entire block of text, that is relatively easy (simply pipe every paragraph into the script, and blindly replace it with the script output, which is even keyboardable: select region & C-u M-; tex<TAB>... to overwrite the region with the output of passing the script into a shell-command which tab-completes to that executable Python script), but to analyze it and just color or highlight troublesome negations? Hm. That's not something I've done in Emacs before...)
* Quite a few of them made me unhappy trying to come up with a good positive assertion version: "We couldn't find John anywhere" can be made less negative in a useful way (eg. specifying where you searched), but making it entirely positive is quite painful and lengthy if you have to specify what and where and when you saw all the things which conjunctively exclude John. It's easy to say "I looked through the house and didn't see John" and that is better... but it's still using negation! I don't even know how I would make this fully positive: "I looked through each room of the house and saw X, Y, & Z." "But did you see John? Was he there or not?" "...Please ask me a different question."
"Positive" and "negative", as used here, refer to truth-values and logical structure, rather than emotional valence.
On almost any topic, there are many potential false statements, and comparatively very few[1] true statements. Thus a simple true statement (like "the sky is blue") is usually much more informative than the negation of a similar false statement (like "the sky is not green").
When reading or hearing a negation used in language, you must first process the positive form it contains to understand the entire statement. For example, to understand "the sky is not green", you must first understand "the sky is green", then negate it. Usually, this happens quickly and subconsciously, but it can harmfully slow down or weaken understanding by making you first consider a false idea.
For these reasons, Absolute-English (henceforth Abs-E), where one only speaks in the positive, should be clearer and more honest than current negation-permitting English. I call it Abs-E by analogy to the absolute-value operation in maths, which replaces both positive and negative with only positive. The simple form of Abs-E forbids the words "no", "not", and "-n't" (as in "won't" or "isn't"). The strict form of Abs-E, which may be more effective, forbids all of the following:
The proposal is loosely inspired by the existing E-Prime, which forbids "to be" and all its inflections for its own, different reasons. You could combine the restrictions to make Abs-E-Prime, replacing "the sky is not green" with "the sky appears blue", but I only care about positivity.
Under Abs-E, binary questions ("yes"-or-"no") are less obvious to answer. If your answer would ordinarily be "no", you must instead reply as if the question was open-ended. For example, your reply to "will you be here tomorrow?" may be "yes", or "I will be in the office tomorrow", or "I will stay home tomorrow". This forces you to speak with more information. On average, that makes conversation more fun and lying harder. If your interlocutor knows about Abs-E, they can make questions and answers play out more naturally by replacing all binary questions with open-ended questions, such as "where will you be tomorrow?" in place of "will you be here tomorrow?".
I am serious about following strict Abs-E, at least for some trial time to see its effects. If, in my speech or writing, you find me using a negative form, you are welcome to call it out for me to correct.
Pedantically, there are an equal number of true and false statements (both infinite). Given any one maximum length of statements, there are only finitely many true statements and many more (still finite) false statements.