TBH I prefer this approach to what OpenAI is presenting - if I prompt to present the benefits of X I want the result not openai’s opinion on the matter. Sure, you can add a disclaimer that it’s hypothetical, wrong, whatnot - but not outright decide on what can you answer and what answer will not be provided.
ChatGPT is notoriously bad in “knowing better what you asked than yourself”.
What…the… Why?
That’s a great example - makes me wonder who actually liked it in the first place to sell it - my boss, his boss and basically everyone I knew hated open space. Where did this scourge originate?
What do you mean? Being on instance X federated with Y would you like to have the possibility to not see content posted by people from Y? Does the content include comments? (Imagine weird blank spots in the middle of conversation and people replying to non-existing for you message). Would you like to also not see Y in search results?
I see you wrote that you’re thinking about making it FOSS. What’s the alternative? Paid software/non-free license + Open Source or proprietary? If you’re low on time and don’t have the capacity to maintain (bugfixes/reports from users) yourself then I say proprietary is a no-go. Then about the license - IMO (though I don’t have hard data on that on hand) people much more likely contribute to FOSS as opposed to locked in license + open source model.