The use of ChatGPT and API's Politics issues

[Dent]

While I cannot comment on your state’s censorship practices, I may be able to help your implementation of GPT-3 to dodge the subject. You might be able to make use of Anthropic AI’s “alignment-checker” pipeline, which I have summarized here, along with a video explanation:

How to set parameters to only answer prompts related to landscaping for example or plumbing etc?

This video describes a pipeline that Anthropic AI uses to moderate their model. Essentially, you get the query from the user, generate a response, then have a moderation model critique said response using a sort of “constitution”, then revise the response according to said constitution, and finally display the response. [First look - RL-CAI/Madison/Claude (fine-tuned 52B) by Anthropic - Announced Dec/2022 (RLAIF v RLHF)] I haven’t implemented it with GPT-3 yet, but it seems like it…