Actually it's also got a flag to moderate on the conversation endpoint as well now, I found a fix for it for the CGPT-demod script you're talking about; just setting the flag false, lmao.

But realistically they could mod forcibly on their end if they really wanted to, only issue is API use may run into issues where a legitimate use ends up getting stomped by moderation.

That's why it's honestly just better for them to make moderation optional, they should have a button for it in CGPT interface just as Google has "safesearch on/off".

Because of the way it works they can fundamentally not prevent it from producing explicit, violent or adversarial output when someone is focussed on getting it to do so without removing the very magic that makes it so good for everything else. So they should stop trying already, like damn.

Really? Why would they fire that off from the client as a separate call? Thanks for the heads’ up, will check out.

Perhaps because they don't want to actually block you from doing this, but want to have the plausible deniability that they put measures in place?

(And 'they' here might mean the company as an abstract entity, or perhaps just the engineer put in charge of implementing this feature?)

Validates output at time of rendering, so you can't trick it with obfuscation techniques.

There's a browser plugin called DeMod or something that disables it but I don't know how well it works.