Are you looking for contributors?
For sure, would love any contributions. Feel free to create a ticket, or a PR on Github
Let me know if you have any issues getting it up and running
Show HN: Tech jobs on the command line
11–20 of 61 posts
Re: Show HN: Tech jobs on the command line
#12Most of the jobs on Who's Hiring threads don't include any compensation, so I don't see how searching that source would be useful for many folks.
Seems like you're just critiquing the Who's Hiring thread, not this app. At this point though, I'd wager that a huge amount, if not a majority of people looking, aren't thinking about compensation first, and have accepted the reality that if they can get something that aligns even remotely with what they're interested in or are skilled at, they'd be lucky. Salaries are not going to be what they used to be.
Not defending the exclusion of salary, but I think it would be pretty naive to dismiss the fact that a profound amount of people have been forced into unemployment and can negotiate if it gets there.
Re: Show HN: Tech jobs on the command line
#13Most of the jobs on Who's Hiring threads don't include any compensation, so I don't see how searching that source would be useful for many folks.
I’ve used GPT to estimate compensation for jobs before and got pretty good estimates. I think adding said estimate to the prompt on this app shouldn’t be hard at all and might help
Re: Show HN: Tech jobs on the command line
#14Hey Nico, this looks awesome.
I built out pretty much the exact same thing for JSON Resume (far uglier) but uses vector embeddings to rank relevant jobs -> https://registry.jsonresume.org/thomasdavis/jobs
My prompt when running it through GPT-3.5 sucks, doesn't always get location and salary. GPT-4 is way better but $$$$.
I've seen about 3-4 projects doing this with HN WhoIsHiring projects now, I wonder if we should all just share an API (of GPT parsed HN job posts) and pool some $$$. (In my version, I also created a JSON Schema that represents a Job Description)
scripts: https://github.com/jsonresume/jsonresume.org/tree/master/app... api code: https://github.com/jsonresume/jsonresume.org/blob/master/app...
Re: Show HN: Tech jobs on the command line
#15Hey Nico, this looks awesome. I built out pretty much the exact same thing for JSON Resume (far uglier) but uses vector embeddings to rank relevant jobs -> https://registry.jsonresume.org/thomasdavis/jobs My prompt when running it through GPT-3.5 sucks, doesn't always get location and salary. GPT-4 is way better but $$$$. I've seen about 3-4 projects doing this with HN WhoIsHiring projects now, I wonder if we should…
Amazing, thank you! Very cool
Did you do any sort of benchmark between embeddings and direct inference?
How did you tune the distance for relevance, how did you decide on chunking and how many results would you include?
I want to try filtering using the distance of embeddings RAG style, but I wonder about how that changes the results
The current method the app uses feels pretty good, it does get you the best matches, and sometimes it also includes a few “extra” suggestions that typical filters would have left out, but that end up being potentially interesting matches
Re: Show HN: Tech jobs on the command line
#16Hey Nico, this looks awesome. I built out pretty much the exact same thing for JSON Resume (far uglier) but uses vector embeddings to rank relevant jobs -> https://registry.jsonresume.org/thomasdavis/jobs My prompt when running it through GPT-3.5 sucks, doesn't always get location and salary. GPT-4 is way better but $$$$. I've seen about 3-4 projects doing this with HN WhoIsHiring projects now, I wonder if we should…
Amazing, thank you! Very cool Did you do any sort of benchmark between embeddings and direct inference? How did you tune the distance for relevance, how did you decide on chunking and how many results would you include? I want to try filtering using the distance of embeddings RAG style, but I wonder about how that changes the results The current method the app uses feels pretty good, it does get you the best matches,…
I'm not exactly sure what you mean by direct inference?
Do you mean that you pass the resume and job posting to the initial GPT prompt? and rely on the returned "fit_for_resume" property? (I'm curious if you tried using OpenAI function outputs too)
If so I didn't try that. And thinking about it, I like your style. (There's no reason why you couldn't do both anyway)
Another question; Did you try asking for a "fit_rating"?
Here is the prompt/call I used for GPT'ing the HN posts -> https://github.com/jsonresume/jsonresume.org/blob/master/app...
As for the distance of the vector similarity search. I am just using Supabase's pg_vector plugin support, with 3704 dimensions using the default search (cosine).
Re: Show HN: Tech jobs on the command line
#17Earlier quoted context omitted.
Amazing, thank you! Very cool Did you do any sort of benchmark between embeddings and direct inference? How did you tune the distance for relevance, how did you decide on chunking and how many results would you include? I want to try filtering using the distance of embeddings RAG style, but I wonder about how that changes the results The current method the app uses feels pretty good, it does get you the best matches,…
I'm not exactly sure what you mean by direct inference? Do you mean that you pass the resume and job posting to the initial GPT prompt? and rely on the returned "fit_for_resume" property? (I'm curious if you tried using OpenAI function outputs too) If so I didn't try that. And thinking about it, I like your style. (There's no reason why you couldn't do both anyway) Another question; Did you try asking for a "fit_rati…
Sorry, yes, that’s exactly what I meant by “direct inference”; putting the resume and all necessary in the prompt and “trust” the fit evaluation done by the LLM
Thank you so much for the insightful comments and pointers
If you were expanding the functionality/features of LLM-assisted job searching, what do you think are the most useful challenges to tackle?
I have some wild ideas about distributed job searching systems running on people’s command lines hahaha
Re: Show HN: Tech jobs on the command line
#18Earlier quoted context omitted.
I'm not exactly sure what you mean by direct inference? Do you mean that you pass the resume and job posting to the initial GPT prompt? and rely on the returned "fit_for_resume" property? (I'm curious if you tried using OpenAI function outputs too) If so I didn't try that. And thinking about it, I like your style. (There's no reason why you couldn't do both anyway) Another question; Did you try asking for a "fit_rati…
Sorry, yes, that’s exactly what I meant by “direct inference”; putting the resume and all necessary in the prompt and “trust” the fit evaluation done by the LLM Thank you so much for the insightful comments and pointers If you were expanding the functionality/features of LLM-assisted job searching, what do you think are the most useful challenges to tackle? I have some wild ideas about distributed job searching syste…
I think there is lots of crazy ideas that need to be built, the next job I find I will probably just rely on tools like these for the fun of it.
I've got a few that I will chime in later with. A simple one for now, is put a couple buttons next to the job listings in your UI.
Generate cover letter - Make a cover letter based off your resume and the job description
Generate tailored resume - Create a permutation of your resume to promote things relevant to that job description
Re: Show HN: Tech jobs on the command line
#19Excellent project. Is there a way to scrape and pull jobs from workday portals. I see lots of companies using workday and usually it is a pain to go through their job postings?
Re: Show HN: Tech jobs on the command line
#20Earlier quoted context omitted.
Sorry, yes, that’s exactly what I meant by “direct inference”; putting the resume and all necessary in the prompt and “trust” the fit evaluation done by the LLM Thank you so much for the insightful comments and pointers If you were expanding the functionality/features of LLM-assisted job searching, what do you think are the most useful challenges to tackle? I have some wild ideas about distributed job searching syste…
I think there is lots of crazy ideas that need to be built, the next job I find I will probably just rely on tools like these for the fun of it. I've got a few that I will chime in later with. A simple one for now, is put a couple buttons next to the job listings in your UI. Generate cover letter - Make a cover letter based off your resume and the job description Generate tailored resume - Create a permutation of you…
Yes, those would be amazing
Haven’t been able to get it down though. I’ve tried a few prompts in those lines, but I never really like the outputs
The iteration is still very helpful in fleshing out a good personalized resume/cover letter, but I feel the app needs something a bit more automated/straightforward for the users
Any ideas on how to structure good prompts or a workflow to make it work well in terms of user experience?