I actually think this idea is not good, and would oppose its widespread adoption. For level-setting, I also want to say that I upvoted the post as I think it's an idea worth thinking about.

I have noticed in the last few years, many services have been rolling out more and more features like this already -- not so much "anger translators" but other sorts of suggested replies, etc. My problem with these is that it feels very intrusive, the computers intruding sometimes into our most intimate lives. For example, GMail's suggested replies and autocompletes show up on all messages if not disabled. I would be fine with this for pro forma interactions, such as customer service reps or whatever, but they also show up when I'm conversing with family and close friends. 

The problem is that it feels impossible to just completely ignore the suggestions - either I want to accept one or else I feel myself changing my intended reply intentionally to avoid one.  Either way, the system is changing how I would communicate with my loved ones in a way that I really dislike. It reminds me one of the most memorable lines from the Matrix, (from memory, not verbatim) "1999, the peak of your civilization. Of course, I say your civilization, because as soon as we [AIs] started thinking for you, it really became our civilization." To the extent that AI can automate more and more work that seems great to me, but automating interactions with our friends and family sounds like dystopia.

I think this is a clever and interesting application of GPT. I’ve downvoted the post. Blunting feeling by filtering it through a robot is… nasty. I’m most opposed to the idea that this should be implemented on the receiver’s side. A machine to shield cheating partners from having to read a “fuck you” is a negative; I don’t want it in the world.

An implementation that only allows optional translations on the sender’s side is better, but still not something I like; RamblinDash’s comment covers the issues there well.

The second-order effect of widespread adoption, of course, is that humans learn to distinguish GPT translations from actual communication, and learn to infer "ah, I see he was really mad, he had to run his actual message through GPT". Actual angry messages would then convey even more anger, since the person had the option of passing them through GPT, and chose not to do it.

As an aside, the NVC versions are still weirdly self-centered, they're pure statements of personnal preference with no attempt to understand the other person's point of view.  And in a weird way, "I feel angry and betrayed" packs more punch than "fuck off!", the latter is emotional and said in the moment, you know the person who said it will probably regret it, but the former feels like it was carefully examined. 

Overall I think it's an interesting idea, much worse sounding apps have been very successful.

I agree with the other commenters that having GPT-3 actively meddle with actual communications would feel a little off. However, I'm excited by the potential of using this kind of a prompt to help people practice NVC by feeding it sentences and having it rewrite them - even if it doesn't get everything perfectly right, this could be a cool "get practice using NVC" app. (Then it could also be used for rewording your actual messages in an NVC way, but if it was a separate app that you yourself had to copy-paste things to/from, it wouldn't have the intrusiveness aspect people were concerned about - it'd only do it if you made the active choice of using it that way.)

This sounds like an interesting idea, it would be nice to have a tool that reminds us to be our better selves. However, it seems like it'd be quite problematic to let GPT mediate our communications. Besides the issues discussed in the other comments, I also think letting GPT handle the translation encourages a more superficial form of NVC. I think the main reason NVC works is not that the framework itself lets people communicate using non-violent language. Rather, it works because using the framework encourages people to be more emotionally aware and empathetic.

As a sender, NVC helps me because:

• It makes me more aware of the inferences I am making (which may be false) based on my observations (which may not be complete). It reminds me that what I perceive is only my interpretation, which may not be true! 
• It helps me pay more attention to what I'm feeling and what I'm lacking, so I can focus more on problem solving (i.e. finding ways to meet my needs), rather than emotional arguments. 
  • Note that sometimes, cooperative problem solving is not our goal, in which case we may not want to use NVC.

As a listener, NVC helps me because:

• It reminds me that people usually have a valid reason why they are upset, which helps me be more empathetic. For example, I used to think people were angry at me because I didn't do what they say, but later realised it was because they genuinely found my actions to be upsetting (e.g. they may find messiness to be distracting, whereas I don't notice it).
  • Note that this is not always true, such as when someone is saying something to manipulate you.

My concerns with using GPT to handle the NVC translation are as follows:

• I suspect an NVC translator would encourage people to "outsource" this thinking to GPT. This would lead to people following the framework without genuinely going through the process of thinking through their (or their partner's) emotions and needs. This means people don't really get to practise the NVC skills, and so don't truly benefit from NVC.
• Knowing that others may be using a translator may also make the conversation feel less genuine because it becomes easy to fake it (e.g. maybe they are actually really mad at me and can't be bothered to make the effort to go through the NVC thought process, and are just using the translator because they believe it will get a better response).
• When it's presented as a translation, it gives the impression that the translation is the real answer, rather than just one of many possible answers.

(Also, I think some of the examples reflect a different problem that won't be solved by NVC translation. For example, I think a better approach for the covid vaccine example would be asking the other person why they believe what they believe, rather than asking them to read the research with you.)

The idea of a tool to help open up the conversation is interesting though, so here are two possible alternatives I can think of (which may not be feasible):

• Instead of translating your words, the app detects messages with strong negative emotions, and prompts you to reconsider when you send it, similar to how Outlook reminds you if you mention "attachment" in your email but don't attach any files. This should be something that is enabled by the user, so it's like a reminder from our calmer selves to our more impulsive selves to think through before sending.
• Instead of providing a single translation, the app suggests possible feelings/needs based on other people's experiences, while making it clear that yours may be different. For example, "Sometimes people say X because they are feeling Y1 and want Z1, or because they are feeling Y2 and want Z2. Do you feel like this applies to you? Or maybe you're feeling something else?"

Here is a business plan:

Make a free messaging application that will make your messages sound friendlier and smarter. (Also, gramatically correct. Essentially, advertise it as "Grammarly for text messages".) Keep it free until you get the majority of users. Then allow them to choose to pay a little money to make them sound even friendlier and smarter. Then gradually make the non-paid version sound normal, or even slightly hostile and stupid.

Actually, if you are Google, make this a standard Gmail functionality. You already have your users sufficiently locked in. ;)

I love this and would love to collaborate. I've been thinking of more of a training system, social connection, and inner exploration app. I do think one issue with blindly translating into nvc is we don't develop the ability to process our own feelings that come up.

This is definitely a fantastic idea. However the usage will be more attuned towards institutional use rather than a formal communication between friends. 

If i am talking to a friend or a colleague this would really make the communication in effective and might loose camaraderie.