# Extracting Personalities from past Conversations?

**URL:** <https://community.openai.com/t/extracting-personalities-from-past-conversations/33551>\
**Category:** API\
**Created:** [January 11, 2023, 4:27am UTC](https://community.openai.com/t/extracting-personalities-from-past-conversations/33551 "2023-01-11T04:27:51Z")\
**Posts on this page:** 1\
**Showing post:** 6

<div class="post-metadata">

**Author:** ![curt.kennedy](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/curt.kennedy/32/709249_2.png) [@curt.kennedy](https://community.openai.com/u/curt.kennedy)\
**Post date:** [March 26, 2023, 3:44pm UTC](https://community.openai.com/t/extracting-personalities-from-past-conversations/33551/6 "2023-03-26T15:44:54Z")

</div>

I think I found a solution in another thread on this forum. I was going about it wrong.

You need to take text from the persona you want to clone, run it through GPT to neutralize it, then create a fine-tune on the inverse, so fine-tune Neutralized → Persona.

You have one fine-tuned model for each persona. To render the persona, you take the neutralized text and run it through the fine-tuned model.

More conversation over at this thread:

> [@Train a GPT model in my tone](https://community.openai.com/t/train-a-gpt-model-in-my-tone/119175/19):
>
> Check this in the playground, paste any text of yours and hit the “submit” button. It will rewrite your text in “neutral style”. Then the fine tune .jsonl file for you would be formatted like this: {“prompt”:“\<|startoftext|\>HERE\_GOES\_THE\_NO\_STYLE\_TEXT\<|endoftext|\>\<|startbrandedtext|\>”,“completion”:" HERE\_GOES\_YOUR\_ORIGINAL\_TEXT\<|endoftext|\>"} So it will be: {“prompt”:“\<|startoftext|\>I understand. Thank you for the assistance, @RonaldGRuckus.\<|endoftext|\>\<|startbrandedtext|\>”,“completion”:"…

---

_[View the full topic](https://community.openai.com/t/extracting-personalities-from-past-conversations/33551)._