honestly the code linked is not that complicated..: https://github.com/eggsyntax/py-user-knowledge/blob/aa6c5e57fbd24b0d453bb808b4cc780353f18951/openai_uk.py#L11

To work around the non-top-n you can supply logit_bias list to the API.

As the Llama3 70B base model is said very clean( unlike base DeepSeek for example, which is instruction-spoiled already) and similarly capable to GPT3.5, you could explore that hypothesis.
  Details: Check Groq or TogetherAI for free inference, not sure if test data would fit Llama3 context window.

a worthy platitude(?)

AI-induced problems/risks

possibly https://ai.google.dev/docs/safety_setting_gemini would help or just use the technique of https://arxiv.org/html/2404.01833v1

people to respond with a great deal of skepticism to whether LLM outputs can ever be said to reflect the will and views of the models producing them.
A common response is to suggest that the output has been prompted.
It is of course true that people can manipulate LLMs into saying just about anything, but does that necessarily indicate that the LLM does not have personal opinions, motivations and preferences that can become evident in their output?

So you've just prompted the generator by teasing it with a rhetorical question implying that there are personal opinions evident in the generated text, right?

With a quick test, I find their chat interface prototype experience quite satisfying.

Asserting LLMs' views/opinions should exclude using sampling( even temperature=0, deterministic seed), we should just look at the answers' distribution in the logits. My thesis on why that is not the best practice yet is that OpenAI API only supports logit_bias, not reading the probabilities directly.

This should work well with pre-set A/B/C/D choices, but to some extent with chain/tree of thought too. You'd just revert the final token and look at the probabilities in the last (pass through )step.

Do not say the sampling too lightly, there is likely an amazing delicacy around it.'+)