#Getting links to online articles.

1 messages · Page 1 of 1 (latest)

hearty juniper
#

I've found that getting links to online articles is often broken with GPT 4o. Many links are broken, out of date, or irrelevant to what I'm asking for. So, I have two questions:

  • Getting Links with ChatGPT: how can I improve the accuracy of requesting links with GPT 4o?
  • Alternatives: why do alternatives such as Perplexity seem to perform better on finding online links?
zealous flumeBOT
#

Hi @hearty juniper. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

#

Regarding your first question on improving the accuracy of requesting links with GPT-4o, it's important to note that if a URL you're trying to reference is partially model-generated, the link output by ChatGPT won't be clickable. To make a link clickable, your custom action will need to output the full, qualified URL for the model to reference. This includes all necessary components, such as the scheme (http or https), domain, path, and any query parameters. Here are some steps you can follow:

  1. Check URL format: Ensure the URL starts with "http://" or "https://".
  2. Validate domain and path: Confirm the domain is correctly spelled and the path accurately leads to the intended content.
  3. Review the custom action's URL generation: If the URL is dynamically generated, review your action to ensure it constructs the URL correctly.

You can find more details on this in the OpenAI Help Article (https://help.openai.com/en/articles/8838458-why-aren-t-my-gpt-links-clickable).

As for your second question about why alternatives such as Perplexity seem to perform better on finding online links, I'm afraid the provided knowledge sources do not contain information on this specific topic. It's important to note that different AI models may have different strengths and weaknesses, and their performance can vary depending on the specific task and how they've been trained. For a more detailed comparison, you might want to refer to the official documentation or research papers of the respective models.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:

#

@hearty juniper kapa.ai is still learning and improving, please let us know how it did by reacting below

hearty juniper
#

@zealous flume That doesn't help. The links are formatted correctly, but they just point to locations that are not relevant to what I asked for.

zealous flumeBOT
#

Let me check the knowledge base for you. One moment! :books:

#

I understand your concern. It's important to note that GPT-4o, like other models in the GPT series, can sometimes generate outputs that are not entirely accurate or relevant. This is often referred to as "hallucination". If you find an answer is unrelated, you can provide feedback by using the "Thumbs Down" button as mentioned in this OpenAI Help Article (https://help.openai.com/en/articles/6783457-what-is-chatgpt#h_78efce1a6a).

In terms of improving the relevance of the links provided by the model, you might want to try making your requests more specific, or asking the model to validate the information before providing a link. However, please note that the model does not have the ability to access or browse the internet in real-time, so it cannot verify the current relevance or accuracy of the links it generates.

If you're still experiencing issues, it might be due to some technical problem. In such cases, you might need to turn off any URL blockers or extensions that you currently have enabled, which could be preventing ChatGPT from loading correctly, as suggested in this OpenAI Help Article (https://help.openai.com/en/articles/7996638-chatgpt-says-there-was-a-problem-preparing-your-chat).

If the problem persists, I would recommend reaching out to OpenAI support for further assistance.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon: