Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Issue with ordered list in response: not included in Markdown #18

Open
ackalker opened this issue Mar 30, 2023 · 0 comments
Open

Issue with ordered list in response: not included in Markdown #18

ackalker opened this issue Mar 30, 2023 · 0 comments

Comments

@ackalker
Copy link

ackalker commented Mar 30, 2023

Thanks for this great extension!

I'm having an issue where an ordered (numbered) list isn't being included in the generated Markdown.

Here is a piece of DOM copied as HTML using Chrome Inspector taken from a conversation with ChatGPT which exhibits the issue:

<div class="markdown prose w-full break-words dark:prose-invert light"><p>When using a large language model like GPT-3, it's important to choose prompts that are specific enough to elicit a coherent response, but not so restrictive that they limit the model's creativity and ability to generate diverse and interesting content.</p><p>Here are some tips for creating prompts that are suitable for use with a large language model:</p><ol><li><p>Keep your prompts open-ended: Avoid prompts that are too specific or narrow in scope. Instead, use prompts that allow the model to explore a range of ideas and perspectives.</p></li><li><p>Provide context: Help the model understand the topic by providing relevant background information and context. This will help the model generate more coherent and relevant responses.</p></li><li><p>Avoid leading questions: Avoid prompts that suggest a particular answer or perspective. Instead, use prompts that encourage the model to think creatively and generate original content.</p></li><li><p>Use natural language: Use prompts that are written in natural language, rather than technical jargon or overly formal language. This will help the model generate more natural-sounding responses.</p></li><li><p>Experiment with different prompts: Try different prompts to see what works best for your needs. Some prompts may work better than others depending on the specific task or application.</p></li></ol></div>

(The <div> has at least one class which I believe was inserted by the Dark Reader extension which I'm using.)

The extension as downloaded from the Chrome Web Store only outputs the following Markdown:

**ChatGPT:**
When using a large language model like GPT-3, it's important to choose prompts that are specific enough to elicit a coherent response, but not so restrictive that they limit the model's creativity and ability to generate diverse and interesting content.
Here are some tips for creating prompts that are suitable for use with a large language model:


 --------

I.e. the ordered list following the first paragaph is missing entirely.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant