Seems like you could do some kind of zero knowledge solution like Microsoft’s Photo DNA for 2 and 3.
For ChatGPT, Grok, and Claude the censorship happens at multiple levels.
1. Censorship at the model training level
2. Censorship at the input box
3. Censorship in hidden system prompt
nostr:nprofile1qyjhwumn8ghj7en9v4j8xtnwdaehgu3wvfskuep0dakku62ltamx2mn5w4ex2ucpxpmhxue69uhkjarrdpuj6em0d3jx2mnjdajz6en4wf3k7mn5dphhq6rpva6hxtnnvdshyctz9e5k6tcqyp7u8zl8y8yfa87nstgj2405t2shal4rez0fzvxgrseq7k60gsrx6zeuh5t only has number 1 because we use models trained by others. Over time we are providing a variety of open models so people can choose the training bias that works best for them.
We do not do numbers 2 and 3.
Discussion
No replies yet.