Apologies for the article's lack of details. Allow me to provide a concrete example:
Me> extract contact email address from the following post:
---
Parative | https://parative.com | Senior Backend Engineer | REMOTE (USA only) | Full Time
Parative is in need of an experienced backend engineer to join its platform team with a focus on API and integration work. As a key member of an early-stage team, you’ll report directly to CTO Jason Zopf and join a growing team of US-based engineers and an established team of developers in Eastern Europe.
We are a remote company; however, we are only able to hire eligible candidates in the United States for this role. Given the size of our team and the nature of our work with customers, we also require candidates to have primary fluency/bilingual proficiency in English.
GPT> The contact email address mentioned in the post is "paige@[parative domain]." The domain part of the email address seems to have been redacted or cut off. Typically, it would be something like "parative.com" or a similar domain related to the company's website. Unfortunately, in the provided text, the domain after the "@" symbol is not fully visible
Same with Chain of thoughts (final email redacted though)
Me> Think step by step to extract contact email address from the following post:
---
... same data ...
---
GPT> To extract the contact email address from the provided text, follow these steps:
Read the Post: Understand the structure and content of the post to identify any potential email address.
Identify Potential Email Address: Look for patterns or mentions that resemble an email address. In the provided text, there is a specific mention: "paige@[parative domain]". This might be an email address with a placeholder for the domain.
Clarify the Email Address: The provided text seems to have a placeholder for the domain part of the email. The domain might be "parative.com" as mentioned earlier in the post.
Reconstruct the Email Address: Considering the context, it's possible that the email address could be "paige@p(--redacted--)ve.com."
That doesn't seem needed at all. Prompting it with "extract contact email address from the following post. It might be obfuscated and require some puzzling." immediately solves it, with much shorter output.
It’s a chain of thought prompt. You literally just tell the LLM to model solve a problem or answer a question by breaking it down into smaller, manageable steps (“think step by step”).
Me> extract contact email address from the following post: --- Parative | https://parative.com | Senior Backend Engineer | REMOTE (USA only) | Full Time Parative is in need of an experienced backend engineer to join its platform team with a focus on API and integration work. As a key member of an early-stage team, you’ll report directly to CTO Jason Zopf and join a growing team of US-based engineers and an established team of developers in Eastern Europe.
We are a remote company; however, we are only able to hire eligible candidates in the United States for this role. Given the size of our team and the nature of our work with customers, we also require candidates to have primary fluency/bilingual proficiency in English.
Apply here: https://parative.breezy.hr/p/235414743556-senior-backend-eng... and feel free to follow send drop me a note: paige@[parative domain] ---
GPT> The contact email address mentioned in the post is "paige@[parative domain]." The domain part of the email address seems to have been redacted or cut off. Typically, it would be something like "parative.com" or a similar domain related to the company's website. Unfortunately, in the provided text, the domain after the "@" symbol is not fully visible