I'm sure some folks will see this as dishonest or unethical, but it feels more like the natural evolution of getting spammed by recruiters.
If recruiters are going to endlessly spam me with their templates and automation, it only seems fair that my response is also templates and automation.
If you email a hacker/programmer whose powers you have heard can aid you in your quest, you should be prepared to endure their intricate labyrinths or spells of invisibility. Their magick is only for those of pure intentions.
As one article taught me about over a year ago respond by sending a well formulated email requesting the salary and job offering. Sometimes it leads to you understanding the market. Sometimes it leads to negotiation for higher salary. Sometimes an amazing new job.
So far this has never failed me. And is far better than ignoring. I only really ignore the crypto companies.
Also, what this does is really separates the wheat from the chaff. If the company can't tell me the salary or the job, it's not a good fit anyways.
Interestingly, what this means is that Google is not a good fit at all. They wanted me to talk to a sourcer, who would connect me to a recruiter. That's too much corporate foreplay for me, especially without even knowing what team I'd be joining.
I wonder if it being so long is part of the filtering process. Only good recruiters will read the whole thing and bother to reply.
I personally believe it is unnecessarily long, formal, and diplomatic. It does not fit who I am and, if I were to read it, I would have the impression of an annoying and insincere corporate speak.
I believe I can achieve all the goals of being polite, respectful, considerate, and filtering for serious offers with a much, much shorter and informal response.
Something like:
Hi X, thanks for the contact. Company Y sounds interesting and I do think I might be a good fit for the role. I am not actively looking for a new position now, but i’d like to know more about the job description and compensation details. Thanks!
This should all be sincere if course. If the company does not sound interesting (like all crypto for me), I only reply a respectful “no” ( ”Thank you for the contact, but I am not looking for a new job right now.” ). Similar when job is for roles that I have no experience whatsoever, which often happens. In this case I also mention that I am not a, e.g., Android engineer (I am a web frontend).
Also, if there is no company or role mentioned, I give the first reply, but obviously removing the acknowledgment that I like the company/role and ask for details about it too.
Taking into account that some sort of automated tool also generates recruiter letters and follow-ups - we witnessed a fight of two computers without any value in it for anyone.
Or rather we have witnessed two computers talking to each other and decided their bosses aren't a good fit at this time (saving the time for both sides while also not missing any potential matches).
Depends on who you ask. Newton would say, "yes". Goethe would say "what do you mean by sound? What if there were two people in different locations? Would they hear the 'same exact' sound?"
My response to recruiters (especially on LinkedIn) is always the same; “Please send over all relevant details for the role you had in mind (JD, company and salary)”.
This filters out about 90% of them, and especially those who’re just fishing for clients.
I used to do the same thing but I got tired of doing that (and they didn’t always respond with the details, but often with another request). Now I just send them to https://polyfill.work.
They have to enter pay, etc. and if it’s a fit for me I’ll hear about it.
(Disclaimer: I made polyfill and it’s a work in progress but I’m looking for feedback on the developer onboarding part so let me have it if it sucks!).
I don’t send them my polyfill profile page because then they’ll have my email and uuid and I want polyfill profiles to be pseudo anonymous.
- I tried a bunch of things on Q4 both while selecting multiples and selecting a single answer:
- Trying to scroll "past" it to push through any CSS padding issues
- Trying to tap the next button
- Toggling through different states to see if the button changes in any way to see if there is JS with a logic bug (spoiler: while the button did show up as expected, nothing changed it's colour or otherwise indicated that it was clickable. Holding the button just caused text on the page to be selected which confirmed that the button did not have the ability to be clicked)
- Reloading the page
- Choosing different answers for Q1-Q3
Dang, that's annoying, sorry about that! And thanks for checking it out so thoroughly. I queued this up and my friend or I will get to it soon. Really appreciate the QA :D
If you want a heads up when it's fixed you can email me at team at polyfill dot work. I will only email you once: when the bug is fixed!
I felt like this blog post ended quite abruptly. I was expecting for the author to show how GPT-3 was able to formulate a response back to the recruiter not just parse out the name and company of the recruiter.
I was worried that that was the direction the article was going to take. My experience with GPT-3 is mostly from playing AI Dungeon, but it seems like it's very eager to go along with anything from the input. It's the ultimate "yes, and..." improv partner. I wouldn't be surprised if it just automatically agreed to every interview request.
Can you prompt GPT-3 "as the person who received message {message}, respond to it." and it understands that it is addressing William from BillCheese (aka, "Hi William...")? Perhaps the best you may be able to do with the current model capabilities is something like "response to message {message} by thanking the sender and telling them you are not interested right now but will get in touch if that changes."
Yes you can, you should create an account and try it out. A fun example I just did
Respond to this email, pretend to be a pirate called Old Blue Bill who is very interesting finding out more about these job opportunities.
"Good Afternoon,
I have 4 brand new roles available, please see details below. I also have an Engineering Manager position becoming available in Leeds (tech is Java/Kotlin), so if you have Leadership/Management experience and want to help an exciting company build a new bank then get in touch as well (the company ae financially stable, part of a £1Bn organization and just received around £30M in funding).
If interested please send me your up-to-date CV and we can set up a call to discuss."
Good day to you, stranger. I be Old Blue Bill, the terror of the seven seas. I be interested in these job opportunities ye be havin'. I gots me a mighty fine CV what'll make ye sit up and take notice. Arr!
Ye best be gettin' in touch with me soon, lest I take me wrath out on yer crew. Avast!
Have you had a chance to experiment with whether GPT-3 prompts can be used to dynamically construct the response? For example, "if the messages describes a frontend role, say I am not interested, and if it is a backend role say I am interested."
> This solution worked well for the handful of emails I tried it on. I’m planning to run this on a cron to save myself some time and automatically maintain recruiter relationships.
Maintain recruiter relationships?! You're sending a glorified autoreply that plugs in a couple values. That is not maintaining a relationship. Luckily, there's no relationship to maintain, because the recruiter probably just blasted out an automatically-generated message to a list of contacts in the first place.
This sort of thing makes me sick. It's an abominable distortion of human interaction, and it makes our society worse.
Someday, the recruiters will also start using GPT-3, and all recruitment conversations will just be transmissions between different GPT-3 instances, creating a massive hive mind of GPT-3s that brings about the singularity.
Pretty sure this is happening already. I started to get some messages on linkedin that include some details from my descriptions, but it feels super unnatural, like a template was filled with some data mined content...
9 of 10 recruiter emails I get have 3 or 4 paragraphs leaving me none the wiser about the company, the product, the role, or why they thought I'd be interested. At most I get a vague idea of the sector. I hate to say it, but the only ones that aren't always rancid corpspeak are the ones I get from big tech. I expect GPT-3 to set a slightly higher bar. At least GPT-3 fools me once in a while. Recruiters never fool me into thinking they contact people with care.
I would expect GPT-3 to do a much better job of making me think they've actually looked at my profile. Most recruiter emails are very clearly the result of a keyword search plus mail merge to insert my name (and sometimes my current employer's name), while GPT-3 would presumably be used to write something more personalized.
Really smart use of GPT-3, if I read it write your prompt asks GPT-3 to use it's magic powers of attention to figure out it's the name and company name you're looking for, then you further ask the response to be in the form of something you can easily extract. The first part of your prompt is the example (Apple computer), and the second part is the real email you want to parse and you give room for the AI to dump it's answer.
I really appreciate the smart ways people are coming up with using the NLP models.
I was curious how GPT-3 would fare with a more elaborate response, so I pasted a random recruiter email and asked it to reply with more information, if the information wasn't in the email.
I am quite astonished by its performance, and this is coming from the guy who made an entirely AI-generated podcast (https://deepdreams.stavros.io)
> asking for information about the job description, salary, and position, if they were not included in the above email
Does this part actually work reliably? For example, if salary info is included in the initial message, will GPT-3 omit it from the response while still asking about job description and position?
Hello <commentator> - Your comment has been selected to participate in our responsecheese testing of GPT-3. This comment has been specifically tailored to respond to you!
It can, codex is better. I envision running a bot farm replacing 100s of negative impact programmers. This will be an improvement! Bonus point using gpt-3 to generate coherent standup slack messages.
I see negative impact being when the boss wants a breakneck pace--marathons at sprint speeds--and won't accept that can't get 99.9 percentile servitude (in tons of ways desiring robotic programmers) at 49.9 percentile wages. If that, I've aced interviews and those shitty homeworks with original cutting-edge research judging which was beyond them, in some cases, and gotten 30 percentile offers. Mostly because I have a tortured man's resume, I got tortured, can't answer simple biographical questions like "where were you working April 2009." [EDIT: Not bitter about the torture, best thing that ever happened to me in a fucked-up roundabout way, in fact I wish I had the memories of the torment, it was a part of my life like any other. I do have many more memories of getting twisted and knee-locked and choked in Japanese Jujutsu the year I was tortured, I love that sport, couldn't get enough] The attitude was totally different before that, for the most part. Like teacher's pet, that kinda shit.
Basically discriminating against veteran status. I didn't commit a crime or get arrested, and not even technically a victim because I didn't cave to the coercion, victis winning was won over. But not a lot I can do about (I don't know) In-Q-Tel limited edition Guantanamo roofies that violate the laws of physics like getting inside the Einstein's concept of an observer, inside the brain. Lived through a two-month autumn, saw the sun leap from solstice orbit to winter orbit, that in practice is superluminal, for me it was.
Back to the vets, yeah that's what's up, they see a lot of backbone they are repulsed by that, can't steal any wages from a veteran he won't take one unit of shit on any scale, if he's a killer, like killed 500 guys (snipers say), he doesn't even have to tell his boss no doesn't even have to really do anything, not stealing candy from a baby anymore. The boss could give him shit if he had say killed 1000 men himself, perhaps then some small amount. But really they would have respect for one another, vets end up working for defense contractors who think it's good that they didn't take shit because then America doesn't take shit. Defense.
We're about to go to war, too, those who forget the soldiers are destined to be forgotten. Not any day now, not for 2 months. But heroism will be considered good again. It's been a while.
.
You should only be able to claim you are hiring if you can pay the same percentile salary as the percentile programmer you desire. Otherwise false advertising. Like insulting even by options traders standards, they'll insult you back if you want to buy shares way below market if the intent is to lie in wait for a sucker. They'll like say "Fuck you" give a speech, for good reason, and not only that, they'll burn you to the person who put you two in touch.
.
Though I recognize I failed to get enough competition going for me simultaneously (due to conditioning under torture, before that I could and I can still) work the club. And there was a long, good economy where I couldn't bang out email after email, like couldn't put in the volume. Not sure how much to blame myself, if at all, given the brainwashing. [Oh fuck, I just flashed now on Sep 2 4:42 Chilean time, the concept of blaming myself also was conditioned.]
Well fuck it then. I don't know what to know. Just be happy to be.
While the title doesn't match the article content, what I really like about this is a notion of semantic regex - learning feature extraction was not a use case for GPT-3 I had imagined, and now my mind is reeling considering other ways this could be leveraged.
that's the point of the article... it's hard to write a regex that works on arbitrary emails from recruiters, but GPT is quite good at extracting information from arbitrary emails.
I explicitly list on my LinkedIn that I'm not interested in "web3" but that doesn't stop the messages. This has me thinking of fun ways to waste a few minutes of these recruiters' time in return for wasting a few (many?) minutes of mine...
I had a long discussion about with a recruiter, since my title is "Not looking for work" and my bio a longer version of "don't contact me". I still get contacted here and there, and I'm very rude when it happens.
It's apparently my fault if their scripts only see "looking for work" and contact me. If I didn't want to be contacted by recruiters, I shouldn't say that I'm not looking for work. He said that he couldn't know that I didn't want to be contacted because he doesn't have time to read profiles.
That was his defence to "this is why people don't like recruiters". Every additional message made me hate recruiters more.
Others have justified it as "maybe your very explicit request not to be contacted is outdated, and you want to be contacted". Nope. Still self-employed.
It would naively seem to me that reading profiles is literally the bare minimum to do the job. If a recruiter can't do more than scrape LinkedIn for keyword matches and send spam, I can't think of a good reason why I should respect their time.
I also explicitly list that I'm only interested in jobs related to language X, but my work history is filled with jobs programming with language X but also Y, Z and a ton of other languages.
Most of all the daily requests I get are for everything but language X. Out of the ~10 messages I get each week, maybe one is related to language X.
Don't think what's happening to you is unique to "web3" but rather that people just skim read the profile on LinkedIn. They simply check if past experiences include whatever they are looking for.
This brings to mind Permutation City (1994), where there exists interactive junk emails. The protagonist uses a program that automatically responds to these emails in a virtual environment in order to determine which ones are spam.
Does this violate OpenAI's terms of service? Or is it OK because you're the only user so it isn't a "production application"? They are quite clear that any AI produced text needs to be explicitly labeled so that nobody could mistake it for
human written.
(I think this is hilarious, but just letting you know so you don't get banned or something.)
It's not obvious to me that this qualifies as "AI-produced". The actual response is a form email, and GPT-3 is getting used as a, like, parser for the recruiter email.
I spent some time in web scraping, and building extractors that work reliably on websites is damn near impossible. GPT-3 automatically extracting out the right data from text is kinda crazy. Imagine scraping LinkedIn without dealing with selectors that change every other day...
Has anyone tried responding to phishing / scams with GPT-3? It seems like a much better use case, scammers are much more annoying and unethical. And you don't have to worry about GPT3 giving a weird response (which idk but the author doesn't seem to realize, machine learning even GPT is unreliable)
I made a habit of never replying to spam. You leak information about your email address being valid if you do. If you don't, the spammer never knows if the email was blackholed or delivered to an actual inbox.
I recently turned all the predictive email, the "Nice to see you too! // Yeah it was fun. // See you!" robot shit gmail proposes. I don't want those proposals. The bias they introduce into my human (when it's a human) interaction is impossible to undo, I turned all all that shit off, if I want to write "Nice to see you! Yeah it was good. // See you!" I didn't even read off the screen what I wrote the first time around, I just literally closed my eyes and typed from memory, incorrectly but so be it. I rather actually push the buttons that I supposedly type, do the work I allegedly do, type every character I supposedly type when it's prose. It's not a waste but even if it were there are much worse things than absolute waste.
But always know they are training wheels, in your dominant language (same idea as dominant hand), you must use no training wheels. Learn the language any way you can, take classes (for sure in person) but at least be native in one language, to the point nobody thinks you're an outsider.
Sourceress on the flip side. And they use the long responses to their long emails to train more. Eh.
Recruiters have been doing this for years, stringing along applicants--ideally into turning down real offers from real people writing for real--with emotionally touching, thought-out...shit at random. To get to the point the applicant prematurely rejects all other offers and then--20 percentile salary offer, non-negotiable, "and then we'll see," and you know and I know you're homeless if you don't take it, but that never gets spoken out loud. Dude they look at all your financials, they build the equivalent of fraud detection to see how much they can lowball you, check your credit history (you knew that, they asked you for it), then they wanted all this endless information from other previous employers (but you never talk to their former employees, no boss's resume of references that worked for him to see how they really felt about it). So in response, first, declare you forfeit all stock options, unconditionally. Then, ask to talk to the people you'll be working with. Then, ultimatum offer, and if you end up on the street because of procedurally generated emotional commitment (which turns out is a liability in court, coming soon), hey, Daniel Cussen will still talk to you, I'll still listen to you, I'll give you when you beg, I'll vouch for you as a witness, I'll remember your name, I'm doing all those things where I live every day with all the awesome beggars--they have so many stories--that took the bait in some capacity.
I'll treat you just like if it were the flip side, as good as I wish you treated me if I got evicted.
And after that, accept that it's a job and subordination. And then do the job, it'll suck it's work, come on, most of the money still goes to people's salaries (this is in a transition and is shifting dramatically, money spent on training is absolutely exploding at the expense of salaries, to my and therefore your monetary benefit if you end up on the street, https://www.fgemm.com coming soon).
> Assuming I get four such emails per week and that it takes two minutes to read and respond to each one, automating this would save me about seven hours of administrative work per year.
Am I the only one thinking that it's obviously not how it works? Not even considering the time it took implementing that.
I mean it's a fun project, but I don't see the need to justify it with "it will make me more productive".
While it’s a nice concept I agree it’s probably not the best fit for the use case. I also don’t understand the point of recruitment spam. What’s the purpose of sending 5 follow up emails. I find it absolutely annoying and would never respond back to an unsolicited email. Surely had they enough applicants for an appealing job, they wouldn’t have chased that much.
To begin with, the average recruiter was hired in the last three months and will last three more months before looking for a new job. They have been equipped with a series of templates and told to customize them.
The goal of the recruiter is to make money by acquiring a candidate, presenting them to a company, and having the company hire them. Note that the recruiter does not actually work for the hiring company -- they have no relationship with them whatsoever, yet. The recruiter's company is paying a minimal salary with an additional fee based on the salary of the candidates who get hired through this process. A particularly scummy recruiting company pays no salary at all, and considers the recruiters to be independent contractors. The recruiter's company has someone in the back office who is manually or automatically scraping Indeed, Dice, Monster, whatever in order to get job listings.
At this point you can see that a recruiter is a speculative spammer.
> What’s the purpose of sending 5 follow up emails
because people often respond (positively) on the 4th - 5th sales email you send, even if they ignored the first, and anyone who's truly pissed off will have just marked it as spam already or blocked you.
I understand it would be better if that wasn't true, but it is true, and that's why people send automated follow-ups.
I tried the five most recent messages I received and it worked as expected for all of them. I imagine that I'll encounter some that don't work, and at that point I'll try adding more examples to make the model more robust.
I've only recently started playing with these models, it didn't occur to me you could ask it to parse content and return a structured representation. That's pretty dang cool.
After having toyed with it for a couple more days, I noticed it sometimes returns malformed JSON with extra tokens. E.g.
{"name": "foo", "company": "bar"}</code>
That's the only weird response I've seen so far, so I just work around it with regex. But if I start seeing other problems with the completion I might try tuning the prompt. Maybe more explicitly telling it how to format the two pieces of data in the output. Got that idea from here: https://twitter.com/goodside/status/1559801520773898240
Wonderful. I think this is also the exact right amount of effort for those recruiters that tell me they like the .Net experience on my LinkedIn profile (there's none, really, I do mostly Java).
If recruiters are going to endlessly spam me with their templates and automation, it only seems fair that my response is also templates and automation.