Hacker News Reader

Comment by rcfox | Hacker News Reader

That sounds like a good idea, but I do wonder if it's a little too... safe?

Every job I've ever taken, there were bullet points in the requirements that I didn't have. And every job has been in a different industry. (Granted, this is only 5 job hops in over 15 years) I'm not really sure I'd want to be perfectly qualified for a new job. Part of the fun is learning new stuff.

Of course, I do understand that any job is better than no job, and it's much easier to land one where you do hit all of the bullet points.

View on HN

This is a really good point. I've also moved upwards into jobs I don't technically meet the requirements in most of my roles. I wonder if an AI tool could generate a new resume based on your existing resume and the job spec for a role to find the best intersection of the two in order to increase your chances of getting an interview...

The idea of using AI to tailor a resume to a specific job spec is promising. Although there isn't direct research on generating resumes using language models, I found related studies in MirrorThink.ai that provide insights into this application. For example, [1] demonstrates the potential of using prompt-based learning for extracting information from resumes with only a few labeled examples. Another relevant study, [2], explores the tradeoff between removing gendered information and maintaining useful job-related information in the resume screening context.

These papers suggest that AI models could be employed to analyze your existing resume and the job specification, and then generate a tailored resume that highlights the most relevant skills and experiences. The main challenge lies in striking a balance between tailoring the resume and maintaining an accurate representation of your abilities.

[1] A Few-shot Approach to Resume Information Extraction via Prompts - 2022: https://arxiv.org/search/?query=A+Few+shot+Approach+to+Resum...

[2] Degendering Resumes for Fair Algorithmic Resume Screening - 2022: https://arxiv.org/search/?query=Degendering+Resumes+for+Fair...

This is exactly what i have been working on for few weeks but not been able to get a good final results. I want to make sure that AI is not overselling my skills or completely deviating from my current experiences/skill set when trying to tailor resume for a job post.

This is an interesting problem, I might start by having ChatGPT try to infer a complete list of tools and skills each position involved along with a confidence score (even those you didn't originally tell it about)

From there you could allow it to remix the skills while maintaining an average level of confidence greater than some number: so it'd be allowed to include things slightly out of your wheelhouse only if most of the job skills matched up perfectly.

You wouldn't need the math to check out perfectly there, the score would just be a heuristic it could use internally

Cool, i should try it..so far i have been working with rephrasing the work experiences description to fit a job description using GPT3.5 api. Still have not engineered the prompt to get reasonable output.For tools and skills , i have a prefilled dictionary which more or less represent my expertises. task of GPT is select top n skills/tools and put them in final result.

Another challenge is to get the AI generated output to fit in a page and preserve original formatting

yeah using chain of thoughts to tackle it. This is relatively simple

Is this not a matter of training? once you know career moves on resumes and how experience can provide the next jump in role it'll then isolate those roles for you. same for cross industry successful moves. I'm sure this is how LinkedIn does this although it's never perfect.

recent advances would allow a platform to conversationally review your CV and probe you're desires to help with recommendations. super interesting space.

> Every job I've ever taken, there were bullet points in the requirements that I didn't have.

This. And you're like most people.

Most job descriptions and requirements lists are describing the "dream candidate". Very few employers actually expect anyone to have every requirement in the list.

AI is statistics based. It's not going to give you only 100% matches.

Reply on news.ycombinator.com