To be clear:
- randomly filtering "too many" resumes is pretty much allowed (I think)
- but must be actual random independent of the resume (and can be in multiple layers, i.e. random filter > pre-select > random filter > select)
- this isn't the case for AI as the random aspect isn't done as the random aspect is not independent of the actual resume evaluation
- in general you can't make sure the AI doesn't apply systematic biases, and there is high indication that it does do so
- for humans you can train them and order them to ignore their biases, this won't work reliable either _but now you delegated the responsibility of illegal biases to the hiring personal violating the order_. But for AI usage you are responsibility no matter what you tell it. Lastly you can technically "show/proof" a specific used AI is highly biased in a specific contexts, which for human employees is technical possible but practical not really practical. So this moves "specific mostly deniable" cases, into "systematic proven bias" teritory. Or in other word legal risk goes from "limited/no issue" to "people can systematically f-you over if they know you use AI for hiring".
Due to acting like an irrational gambling machine, I agree it can have unwanted indirect discrimination effect in general. But it will probably not differentiate "on the grounds of religion or belief, disability, age or sexual orientation". It is possible, but that would take a lot of work for the lawyers to prove to the court.
I believe the more interesting part is that the EU AI Act (still not in force in this regard until 2 December 2027). This will be clearly a high-risk AI system: "AI systems intended to be used for the recruitment or selection of natural persons, in particular to place targeted job advertisements, to analyse and filter job applications, and to evaluate candidates".
Which does not mean prohibited, but it could later turn out that LLMs will be excluded from being used in high-risk AI use cases (falling under article 6 with no exemptions).
Considering that none of the standards are published yet, I have absolultely no idea how they will ensure compliance with the following parts of Article 10 when using LLMs for such tasks: "(f) examination in view of possible biases that are likely to affect the health and safety of persons, have a negative impact on fundamental rights or lead to discrimination prohibited under Union law, especially where data outputs influence inputs for future operations; (g) appropriate measures to detect, prevent and mitigate possible biases identified according to point (f)"
I don't think that's technically possible to do so with LLMs in general at the moment, even with the full cooperation of the model providers. Maybe you can do some meaningful audits for smaller models. But the EU AI Act may end up excluding all the generic "using-LLM-but-not-entirely-sure-why" vibe coded approaches from high-risk use cases (in Annex III). Which would make sense.
Which means there's a good chance this is somehow correlated in one way or another to race/gender/other protected classes in the US, just by the math of everything being correlated to everything.
Which means this is one good lawsuit away from being illegal in the US as well. It doesn't even necessarily have to "win", just do well enough in court to scare away anyone else from using this.
And boy oh boy would I hate to be on the receiving end of this lawsuit, trying to prove that my AI screener is completely in compliance with all hiring laws. That sounds like a nightmare.
It's generally illegal under GDPR Article 22.
> The data subject shall have the right not to be subject to a decision based solely on automated processing, including profiling, which produces legal effects concerning him or her or similarly significantly affects him or her.
Exceptions in 22(2) are unlikely to apply. It's hard to argue that it's truly necessary (a) and consent (c) is almost always unavailable in employment context. (b) might apply, but it requires specific law in EU or Member State to authorize it.
> temperature 0.1 — low, supposedly nudging the model toward deterministic outputs
This is not correct (and is briefly touched on later in the piece when he sets temperature to 0), temperature is not some kind of "deterministic" switch, but rather it affects the sampling distribution (which becomes more "spiky"—but is still very much a distribution).
Well, in theory theory, temperature 0 doesn't really exist. Mathematically, as lim temperature->0, the distribution gets spikier and spikier, the most likely sample goes to almost-but-not-quite infinity and the rest go to almost-but-not-quite 0. In practice, temperature=0 is literally a separate branch of an if statement that just picks the most common sample (using the actual formula that works for non-zero values would cause a zero division).
However, due to things such as batching and even different kinds of floating point imprecisions for different algorithm implementations, the probability distribution itself often differs run-by-run, so what you sample from it also differs.
It does exist very much, even if you go to pure math. Look at the softmax function and take the limit as T->0. It becomes a dirac-delta function. I.e. in a discrete setting (like for LLMs with a finite set of output tokens), probability P becomes one for argmax and 0 for everything else. Only in coding practice it is easer to implement T=0 as a simple if check that directly chooses argmax instead of calculating the limit of some function that includes 1/T quotients. But setting T to zero is in both, theory and practice, turning the usual probability function into greedy sampling.
In pure math, it does not always do that. It becomes a dirac-delta comb with equal weight on every maximum. There can be more than 1 maximum. Setting the temperature to zero turns into greedy sampling, but greedy sampling is not necessarily deterministic as you can have multiple equally optimal options.
Any two tokens ending up with the exact same logit is very unlikely, but not impossible; and as the number of output tokens grows, the odds that it will happen eventually gets higher and higher.
I suppose, to ensure determinism, rank by logit then token ID, so you still have a deterministic winner even if occasionally two tokens get precisely identical logits.
If there's one counterexample, it's not really deterministic.
My point is, deterministic logic matters in certain circumstances 100% of the time. Forcing the LLM to make something unlikely is not good enough because a series of mistakes could very quickly bankrupt the company.
I don't understand the distinction you're drawing. A Dirac delta function is a "simple if check".
What you can do in math is talk about the limit of a series of fractions as the denominator approaches 0, and that's where you get some relation to infinity or -infinity. But the limit can also be any other number, if the numerator also gets closer to 0; or it can not exist, if the function oscillates.
Which is the case with softmax function, as for T=0 you end up with a fraction that either becomes 0/0 or inf/inf [0]. So you do need branching as floating point arithmetic is not gonna get you there.
[0] except for weights that are exactly 0
edit: thinking more about it, one could always express the softmax formula in ways that this could work with floating point arithmetic but it would be very inefficient and sort of pointless
Exactly. While I’m assuming this won’t be news for most here, for those that are still new and/or curious about some more explanation on e.g. the floating-point imprecisions, see this nice article: https://thinkingmachines.ai/blog/defeating-nondeterminism-in...
That's not how limits work. As the temperature goes to 0, the rest goes to 0. That's it. The "almost-but-not-quite" is part of the "goes to".
Let's say f(x) = 3x+1. It's a continuous function. If we let x go to 10, f(x) goes to 31. Not "almost-but-not-quite 31". No, to 31. (If you don't have a continuous function then it's the same argument, but less intuitive to illustrate.)
The implementation does not often differ run by run.
If you use a cluster, or even multiple clusters, and they have non-identical hardware, then two consecutive runs could end up being routed to nodes having different GPU models with slightly different floating point behaviour, or even software differences (e.g. newer GPU offers some feature usable to speed up calculations which older model lacked; same code can use the feature when it is available, fall back to slower alternative if it isn’t). The larger your scale, the greater the odds it will happen
But theoretically, the output of every LLM is seed-driven (or could be if you wrote the software to isolate it) just like any computer software. It's just none of the software written (even llama.cpp AFAIK) chooses to support stable-seeding due to the changes in stuff like CPU/Vulkan/CUDA/Metal differences making it difficult to make consistent.
They could though! Hopefully one day someone implements it into the mainstream LLM-engine software and it gets exposed in the APIs serving the models. It'd do a lot to show folks the "internals" of these models.
CPUs and their execution environments introduce subtle hardware variations, architecture choices, and compiler optimizations that break bit-level consistency.
(same for GPU/TPU, ...)
You don't even need temperature 0, just make a random seed for the sampler part of the input and then its deterministic as a function of the input.
But running autoregressive models at temp=0 tends to expose pathological behavior, because the training process produces a function with a lot of gain so its prone to feedback on its own noise.
Provided:
* If it’s MoE we are talking about, that the duplicate inputs are for the whole batch (yes, your batch neighbours can impact your choice of experts. Blergh.)
* Your kernels are deterministic
* There’s no system wide effort switch that responds to, e.g. work load across the cluster (for a thinking model)
Upshot:
Temperature 0 is not deterministic in probably any existing cloud infra, but it could be for edge inference pretty reliably.
To your quibble on 0.1 being more deterministic - I think it’s a pretty fair summary - we’re going to sample much more from the ‘temp 0’ answer at 0.1 than we would at temp 0.9, no?
E.g:
“Where is the Eiffel Tower Located? One word only.”
“Where is the Effel Tower located? One word only.”
“Where is the Eiffel Tower located? One wor only.”
I’d be very surprised if those got different answers from even a small local model at temp 0.
It is a common misconception, but it is not true even in principle. If I have 2 or more logits which are equal to the maximum of my logits, I will sample uniformly random from them with any temperature, even zero. Sampling from softmax([1, 0, 1]) is still stochastic at temperature 0, because the limit is to sample uniformly from the first or the last element.
Anyway: "GPUs don't do deterministic matrix multiplications" is the biggest source of randomness in LLMs. GPUs put the associativity of the sums in matrix multiplications in arbitrary order, and this has a huge impact on the logits coming out of the neural network.
But this isn't a fundamental property of LLMs, it's just an implementation detail. It's pretty obvious that if you evaluate the matrix multiplications correctly and deterministically sample from the highest-probability outputs, you will have a deterministic LLM.
That’s user-controlled too, not an inherent property of GPUs:
https://docs.pytorch.org/docs/2.12/generated/torch.use_deter...
> torch.bmm() when called on sparse-dense CUDA tensors
And it's not listed under the operations that raise an exception otherwise, so I'm not sure the docs promise that dense-dense matrix-matrix products are deterministic.
You're correct. The confusion arises because we use the word "non-deterministic" when we mean "probabilistic".
I tried to explain it better: https://www.lelanthran.com/chap15/content.html
So “purely stochastic” overstates it a bit: the distribution is computed deterministically, and you choose whether to sample from it or not.
IEEE 754 only specifies precision requirements for certain operations, not precise bit patterns (e.g. for exponentials). So, at least in principle, the same hardware performing the same operation could produce different results at different times, as long as they are close enough to the theoretical answer. I'm not sure if any hardware actually works like this.
IEEE 754 also specifies that many of the basic arithmetic operations are not associative - so any reordering (which is common when batching multiple queries at the same time) will introduce indeterminacy from the perspective of your own query (that is the result for your query will change depending on what other query happens to be processed at the same time, which is not under your control).
Finally, even if we take the case when a query is processed alone, and even if one particular hardware is completely deterministic, the result will be different on different hardware - which can again look like non-determinism if you're sending your query to a load balancer.
So, the math for LLMs is deterministic in theory, but implemented with non-deterministic approximations & optimizations in practice, and their results are then normally used only as a probability distribution to be sampled from.
I've been studying AI for 20 years. What really needs to be added to this statement is:
"An alarming number of people don't understand that LLMs work via purely stochastic processes - and so does human thinking. People do NOT arrive at the same conclusion if merely the weather's different. Worse: with human thinking not only do most people not think this is real, a subset of people will actively fight the idea. Of course, depending on the weather"
If you train two different LLMs and replace what data they "see" in batch n, that doesn't affect the data they see in batch n+1, or any further batches. In LLMs, you can introduce "noise" into the training process, but that noise doesn't really compound.
Humans learn from experience, not from data, and their experiences at age n shape what experiences they seek (and hence train on) at age n+1. A small amount of "noise" injected into their "training", let's say hearing a group of friends discuss a movie while their identical tween goes to the bathroom, can compound into them watching that movie, which can compound into them forming an identity around that genre, and so on, until they're two completely different people, trained on completely different "data mixtures".
Far worse would be different humans having the same weights.
We expect computers to be consistent despite running programs that are not designed to be consistent.
This despite the fact that we have lots of experience of programs running on computers that produces wildly inconsistent outputs.
But for some reason some people choose to assume LLMs should act like a calculator instead of any of those programs.
The average user has very little. A word processor with inconsistent pagination or a spreadsheet with inconsistent totals is rightly seen as faulty.
What I'd really love is an actual number for a "human hallucination rate". How often will a random human
1) claim something that is wrong
2) defend the wrong claim and/or logic even when the problem is pointed out to them
(and this of course outside of the usual topics. In politics? I don't care. In religion? Don't care (well, maybe a bit more than politics). Let's say in physics or popular logic or something like that)
but moreover, to verify a test item you need to make sure that peopel will select the same answers under teh same conditions at different times. people generally forget the specific questions they were asked if you ask them the same questions a month later so being able to get them to answer the same way each time is important. it is assumed the people have some static knowledge of a topic in this scenario.
If you want to consider a statistical examination of how people answer tests and how we assess knowledge and other things in people through surveying you can read about item response theory and rasch analysis.
using low temperature is more deterministic, but the cost is the model becomes "dumber"
After that RL step, you want to stick to the RL distribution, and so keep a temperature of 1.0. Other temperatures will drive the model out-of-distribution.
That is why the sampling step for agents or thinking LLMs are usually kept at a temperature of 1.0.
I don't know for sure, but I would be surprised if it was illegal in my particular US state. You might be able to argue the AI has inherent biases that introduce illegal discrimination in the hiring process, but my understanding is winning I case like that would be very difficult, especially since most employers are very cagey about their hiring process and why they mades a decision.
Show someone a list of resumes with an "applicant score*" and they'll naturally ignore the ones with a low ranking
*scores are generated with AI, mistakes may be made, use only as a guide and verify results
nonetheless, people will defend history as perfect and say those samples, like nepo babies, are "perfect".
I see two possible solutions.
1) Most people won’t be using up most of their luck on this one thing. I mean they’ve got their whole lifetime worth of luck, so you just need to make sure to pick people who still have plenty left. In other words, ageism and/or picking people who’ve never accomplished much are the solutions!
2) We assume working for the company is a lucky outcome. If you make the company a really unpleasant place to work, people will have to use their luck to dodge it. However, luck can only be evaluated against other possible outcomes. The plan, then, should be to set up a competitor (possibly a front) that is a really nice place to work. They’ll act as the “lucky outcome expenditure dump.”
Ah yes, the much revered cosmological fairness constraint.
Any position you have these days is inundated with applications. Most don't meet the qualifications (because in a lot of places say in the US you must apply to jobs to keep with benefits, regardless of what you are applying for), and for the remaining, you'll find that there will always be some that are all similarly qualified. Who do you hire for one position? It sometimes just comes down to luck.
AI doing the job of filtering I can't imagine making the process easier, and more applications are just going to get tossed because of it.
After a few runs it picked things up appropriately. I always got dinged on formal education though.
This stuff is gross.
Also, it doesn't pick up certifications or awards. I tried some PRs people are suggesting with enhancements (https://github.com/Zem-0/hiring-agent), it helps, but overall their ATS is hugely biased towards people with large GitHub contributions to OSS.
As someone who’s run hiring pipelines for technical roles in the past few years, that’s actually a fantastic number. I objectively hate saying that, but it’s true.
35% chance of elevating a technical individual to the next stage with no effort? I’ve seen as many as 100+ applicants an hour even when including a domain specific screener question. That’s 35 “screened” applicants in an hour. Were valid candidates screened out? Yes. Does you still have a candidate pool 35x larger than you need? Unfortunately, also yes.
The volume of applicants is SO HIGH such that your chances of getting moved to the next stage are actually markedly worse if AI isn’t involved. If you didn’t apply immediately (using an AI bot) there’s 50+ people ahead of you, and an exhausted technical leader if they ever make it to your resume.
Referral bonuses exist for a reason.
*According to our proprietary, undisclosed, non-deterministic metric, which may or may not be Math.random
https://stackoverflow.com/questions/16833100/why-does-the-mo...
Gates that reduce resume flow-through are only useful if their reduction is correlated with quality. Otherwise they're just dragging out your hiring process or unnecessarily causing you to ultimately lower your hiring bars.
The volume is infeasible to review everyone for quality, even at an hour scale. The conclusion and solution is inevitable, though I wish it were different. 35% is actually really good if you’re not coming in through a referral.
The current reality is <1% and the person reviewing you is exhausted.
It’s all probabilities in the end. And if an LLM gives you more a more relevant pool vs random distribution, that’s still a net benefit.
Corpo bullshittery at its finest.
If you have 1000 applications for every job, and you know that a bunch of these applications are "a bad fit", to put it mildly, you have to filter. And you cannot realistically give every resume a good, human look. By the time HR would be done, the market has already moved on five times.
So, what is the real difference between being overlooked because HR could only look at the first 100 resumes, or the AI filtered all 1000 resumes down to 100? In the end, a fuckton of potentially great people get their feelings hurt either way.
At 10 seconds per resume, it would take you 3 hours to go through all 1000 resumes. I don't know what you consider "good" and "human", but my human eyes could easily do good enough, fully manual pre-screening at a rate of 1 requisition per day.
Instead of spending all those resources on resume filtering, hire resume blind. Instead of using llms for a thing they are bad at (subjective decision making) use them to build a deterministic process that isn’t.
Use work sample hiring as the filter. Make the work sample automatic to sign up for and judge.
Here's a realistic proposition. HR just wants to inflate numbers so that they seem busy looking for the right fit. Keep posting open for 1 week, manually filter for another week, invite people, employ one. Plenty of people with degrees looking for jobs right now, I don't see what's the issue with just trying one. Companies desperately look for the "magic" applicant that checks all boxes, while also trying to pay them almost minimum wage.
If the first 50 people who apply are all bots, why are you reading resumes in order of submission?
1. Give them some easy leetcode questions. Nothing that a competent programmer would have any problem with.
2. If they pass, ask for a deposit of like $20. Shouldn't be an issue for people who are actually serious.
3. Do more simple leetcode questions but this time on zoom so you can tell if they are using AI. If they pass that they get the deposit back.
(Yeah I know there are real-time interview cheat AI programs but based on what I've seen on demos of them it's super obvious when they're being used.)
Probably not practical but just a thought!
> 30 for personal projects
These are insane weights for scoring a software engineer's resume.
Determinism matters for reproducibility, but do you really want these outputs to be reproducible in this particular case? Making LLM outputs deterministic is relatively trivial, you have to use batch-invariant kernels (if you use batching) and either set the temperature to 0 (don't do that, randomized sampling is here for a reason) or fix the seed (better). It's readily available in a few systems. But this won't make the result more useful, it will just obscure the fact that the agent is genuinely not sure about it - look at the range of the scores it gives! It still won't predict anything but the score will stay the same each time. Do you really want that?
What happens here is they're supplying too little information (just a resume, which is almost at the noise level) and expecting a reply with too broad implications. This is a basic design mistake regardless of whether it uses LLMs. All surveys, tests, laws, and voting systems are extremely sensitive to framing because they work off too little information. But they also don't exist in vacuum, unlike this thing.
For example, 65 points are given for a mix of personal projects and open source contributions. Which is great if your one and only interest is in tech, and you don't have a family, dependents or a second/third job. If you have any of those other things, well the odds seem like they're incredibly stacked against you.
And it makes me wonder how many of these systems are stacked in favour of wealthy people with a near special interest level of obsession with tech and no worries outside of going to college/working a single job in their industry of choice.
That’s a tiny model. No LLM is going to be a perfect and repeatable judge, but a tiny 4B model is like plugging an RNG into this system.
This whole exercise feels like someone vibe coded an ATS and got it to the point where the tests were passing because they decided they should have an open source ATS project.
BONUS POINTS: 5.0
------------------------------
Google Summer of Code (GSoC) participation: +5
In my experience, cold-applying has always worked essentially as a black hole, and LLMs haven't changed that much. The reality is that alternative avenues are always necessary to get the job you want. That could be a third-party recruiter; reaching out to a hiring manager on LinkedIn; or using your network to get referrals. Those continue to work whether the company is using a bone-headed tool like this or not.
I don’t think the point of a lot of this is to optimize your resume. It’s to show how arbitrary these systems are.
You read my mind. If the answer is “no”, then we can ignore this.
But I'd also assume that their competitors are doing something similar so I don't think we as an industry can just ignore that it's happening.
I’m surprised open source contributions count for so much. first I thought was “is that something people actually list in as resume?”. But it looks like it pulls your GitHub account and appends that information.
That kind of unfortunate for anyone who doesn’t use GitHub
Which sort of sounds workable until you scale it up to larger datasets, where at some point compute/time/energy costs will render it non-viable.
I am sure there’s some reasonable rule of thumb estimation on distribution that could be applied based off fewer runs per data artifact, but you’re always going to be trading off against confidence by doing this.
Beyond this, I’d bet that almost no implemented systems that use LLMs for scoring, ranking, or decision making use such a multi-run approach. Partly because people don’t understand their behaviour is stochastic, perhaps because a lot of people without a background in statistics don’t understand what stochastic actually means, and no doubt partly because of budget concerns: if you have to ask an LLM to do the same thing 10, 50, 100 times to get a sufficiently good result, then the cost saving argument is either weakened or completely destroyed.
There is at least one more aspect worth considering in the specific case of resumes/CVs: is the inconsistency of scoring by LLM worse than the inconsistency of scoring by a human following a similar process?
Because the reality is that, even for an experienced recruiter, reviewing hundreds or thousands of resumes or CVs gets pretty fatiguing. People get hungry, bored, tired, restless, irritable, etc.
That inevitably leads to inconsistencies creeping in, so there’s always an element of “luck” (or, perhaps better, uncertainty) as to whether your resume/CV passes screening.
So is that inconsistency better or worse with LLM screening? I don’t know. But, at least, if it’s not worse maybe it doesn’t matter for this specific use case. And if it’s notably better then maybe it’s raised the bar on what “good enough” screening looks like?
(And I’m sure other use cases warrant similar, “does it matter?”, questions, with the answers no doubt landing differently.)
It is actually a very hard to solve problem.
Chickens coming home to roost.
Well done you! It is difficult to avoid architectural complexity, but imho well worth it.
> *SCORES MUST NEVER DEPEND ON THE FOLLOWING FACTORS:*
> - College, university, or educational institution name
> - CGPA, GPA, or academic grades
I don't understand why they would omit these factors from the evaluation.
> But it didn’t. After the company trained the algorithm on 10 years of its own hiring data, the algorithm reportedly became biased against female applicants. The word “women,” like in women’s sports, would cause the algorithm to specifically rank applicants lower. After Amazon engineers attempted to fix that problem, the algorithm still wasn’t up to snuff and the project was ended.
And in another org:
> After an audit of the algorithm, the resume screening company found that the algorithm found two factors to be most indicative of job performance: their name was Jared, and whether they played high school lacrosse. Girouard’s client did not use the tool.
https://www.npr.org/2024/04/11/1243713272/resume-bias-study-...
> Their working paper, published this month and titled "A Discrimination Report Card," found that the typical employer called back the presumably white applicants around 9% more than Black ones. That number rose to roughly 24% for the worst offenders.
It'll discriminate by proxy, basically.
Only hiring MIT graduates sounds great to a lot of tech folks! Automatically rejecting applicants from HBCUs, however, sounds like a lawsuit
As to GPA thing, I think it's just to stop the LLM glomming onto an obvious numerical grade? LLMs like to rank things by obvious dimensions, and whether someone had a 4.0 or a 3.8 in grad school makes very little difference to their performance 10 years down the line.
Just kidding, my resumes are sent to /dev/null like everybody else’s.
——
1: In fact, I will be controversial and say that self-taught engineers tend to be the strongest in their own particular niche, because they are powered by sheer desire to learn and improve. I am routinely appalled by how many people go on forums to ask how to learn a new thing, completely unable to self-direct their learning. I blame the modern school system.
This system would drop a Harvard top graduate for someone having a year of experience in some outsourcing firm.
I worked for a very large job board for the last six years, it's the one you're thinking of. What we found is that the outcomes of paying attention to what school you went to are almost entirely discriminatory, and not predictors of success.
Really depends on the program. In my undergrad program there were some very smart CS students who got great grades that really struggled with the programming. Smart and capable people can be bad at programming and lack many qualities that make for a good hire.
The only drawback I see is that you should compare every pair of CVs for best results, and that grows quadraticly with number of CVs. Of course you can settle for fewer comparisons and not perfect results. But then I'm not sure if you can hit a good ratio of quality and token spend.
1. Set the elo of all CVs to 1000 elo
2. Randomly pair up CVs and compare. Winners gain elo, losers lose elo.
3. Repeat #2 for a few iterations, then remove bottom X% of CVs.
4. Repeat 2-3 until the amount of remaining CVs is small enough to do an exhaustive comparison.
I don't have a mathematical proof, but I suspect that this is a decent cost-effective approximation of comparing every pair (depending on the parameters)
Or compare each one to a reference set? Take 5 resumes of existing employees, rank all candidates against that set, maybe you get some useful level prediction into the bargain
Worse model may not "know" enough to distinguish between a 70 and a 100 candidate, so it's expected that it's output has high variance. But a better model might "know" enough, so it can be more confident and thus more consistent.
It took more time than if I just reviewed the 40 CVs myself, but that was an experiment, and I think it shows the AIs can be trained on your comments. And if there is enough training and a good knowledge system that allows AI to apply the learning in those trainings, it can eventually become a lot more accurate at this task?
> 35 points for open source contributions
> 30 for personal projects
I don't contribute to open source or have personal projects because I don't spend my free time doing what I do 40 hours a week to make a living. My 15 years of work experience is worth a maximum of 25%, so any company using this idiotic system would pass on me immediately. Open source and personal projects are fine, but in no sane world are they worth 65% of a resume's score.
Free software work doesn't imply we work for free. We work on our projects, the stuff that we actually enjoy working on. Nobody is going to work on corporate products without adequate compensation.
I guess there sadly are many nobodies who do this to hope to become somebody.
I wonder if that assumption is bourne out in reality though?
I'd imagine if someone's OSS contributions are enough of a factor that it's worth hiring them, they're not going to drop it on a whim to work extra hours on the day job.
(Assuming you weed out open source contributions like "I made a todo list app in React but licenced it as MIT" or "I fixed a typo in the docs for NextJS". )
Now all my "non-work" time is spent on startup work. And none of that is visible via GitHub.
Even better Wikipedia lists the abbreviation I am familiar with but give a different interpretation of the same words:
https://mathpix.com/careers/apply
Then internally we have dashboards and sorting based on AI agent scoring. I noticed the scoring is imperfect but still saves a lot of time. Candidates scored at or below 2/5 are reliably bad and candidates above 4/5 are consistently impressive and leave thoughtful answers.
The biggest thing is not using resumes. You can’t reliably gage applicants without a writing sample and resumes are the worst form of writing sample. Also you need to be intentional about who you’re hiring for, both to craft the questions as well as grade the responses.
Is it working for anyone, on any level?
For one role we got ~70 applications and all CVs looked obviously AI-written. I don't know whether the people did actually do any of the things mentioned and I don't have the time to find out, so the AI-written CVs are a discard-signal for me. (Either those people delegated a very important task to AI and didn't even bother to check, or they are bad using AI and don't know -- I want neither)
Any CVs that signal they were actually written by a person I will actually look at.
Were those ~70 applications all of them, or were those ~70 applications the result of an AI filtering from a larger amount?
If the latter, are you sure your AI is not filtering out the hand-written CVs and giving you the ones that have been AI-assisted or AI-written (with or without "the usual AI signs")?
Your resume's reception is always affected by random factors, only now you are able to test, debug and technically critique the randomness.
Just roll the dice. I mean, it's not the worse you can do to narrow a subset.
[0] https://github.com/interviewstreet/hiring-agent/blob/main/pr...
In no particular order:
1. The prompt is trying to get the system to do all of the evaluation steps at once. Instead, the system should break down the task of resume evaluation into its subcomponents and have separate prompts for each component. Like "evaluating open source contributions" should be its own task. Same with "assessing the complexity of software projects on the resume." Fwiw, each of the tasks contained within the prompt is woefully underspecified.
2. The prompt leaves spreads of ~10 points up to the LLM, when it's doubtful that humans are that well calibrated. Take for example:
> SCORING CRITERIA Open Source (0-35 points)
HIGH SCORES (25-35 points):
- Contributions to popular open source projects (1000+ stars)
- Significant contributions to well-known projects
- Google Summer of Code (GSoC) participation
- Substantial community involvement
3. The authors of this prompt have left an incredible number of judgement calls up to the LLM, when that's the very thing you want to minimize. Using the same example as above...
- Are all contributions to open source projects with 1000+ stars equal?
- What counts as a "significant contribution"? Doesn't that imply that the LLM has to know or read through all of the commits in like the last ~6 months at minimum for the project to understand what the given contribution meant to the project? That itself isn't impossible with tool usage, but again, that'd be a separate task.
- What on earth counts as "Substantial community involvement"? Why didn't the prompt authors define this, or at least give a few examples?
Honestly at this point maybe someone should build a tool that scans prompts for adjectives...
4. This sort of thing is just asking for trouble:
> SCORES MUST NEVER DEPEND ON:
Candidate's name, gender, or personal demographic information
5. Obviously this one depends on the LLM in question, but instead of writing things like:
> DO NOT RETURN A RESUME SUMMARY. RETURN ONLY THE SCORING EVALUATION IN THE SPECIFIED JSON FORMAT. Analyze the following resume and provide a JSON response with this EXACT structure (all fields are required):...
6. One major thing that's not in the prompt is anything about traceability. This system should be designed so that humans can review the logs and make sure this is working as intended.
7. Another thing that is missing in the file is what I'll call evidence of a theory of coding / coder quality. Most of the examples are designed to have the LLM assess proxies for code quality, not code quality itself. Surely both should be taken into account?
I'm not an expert at evaluating coders. But two pretty basic LLM-answerable thing I would ask is: How well do a candidate's 5 most recent commit messages match the contents of those commits? Do the claimed technical skills on the resume match their GitHub code? (i.e., if they say they know R, is there any evidence of that on their GitHub?)
8. The prompt also seems unaware of what it's asking the LLM to do:
> LIVE DEMO BONUS: Projects with working live demos should receive 10-20% higher scores
(A more charitable interpretation would be that aforementioned CTO was making a joke that didn't land.)
Also, neither "this is not" or "it is" appear at all in the article?
> This non-determinism isn’t a bug you can just fine-tune away, it’s a fundamental design flaw.
However given the time constraints reviewers have, yes, the former (making a resume easy to consume quickly) is a huge help.
While resume's are being filtered left and right, they just make TikTok's on company's dime [1]. What a sad state of affairs.
Also if HR was really useless (or actively hurting the company) they wouldn't still have a job (or they'll lose it eventually). No one likes burning money for no reason. So obviously they are doing something useful.
Not that I agree with this AI approach but when hiring, the real test begins after this initial hurdle
Hooray for incidental non-determinism.
Typically, retrieval should be tied to evaluation metrics, evidence should be linked to scores, and you also need to account for parsing errors.
But personally, I'm weak to these kinds of ATS systems (ugly appearance, non-native English speaker, didn't go to a good university), so if this kind of filtering existed, I probably would have never had a job in my entire life. Come to think of it, even now I don't have a proper job—I just bid on projects at the lowest price and implement them. So maybe it doesn't really matter whether such a system exists or not
You see a lot of frameworks for things like spec-driven development make use of scoring how good the spec/design/plan is and it’s like, uhhh…
This doesn't mean anything. All LLM output is like that.
That said, I agree that LLMs are terrible at grading stuff, except perhaps if you give them a very detailed evaluation grid.
https://github.com/interviewstreet/hiring-agent/blob/main/pr...
One of the weird properties of other people using LLMs is the potential of having oracle access to your opponent. Even if you don't have their exact LLM a good guess at it may be a better model of the opponent than you ever had before.
> LLM is called six times to extract structured information
Followed by
> The default model is gemma3:4b, running at temperature 0.1 — low, supposedly nudging the model toward deterministic outputs.
This is exactly why hiring is even more broken: Because the people looking for candidates are also just as unqualified if not, more.
Using much weaker LLMs to replace the person in charge of the final judgement call is the wrong solution as this is a plain old social problem.
Even if you wanted to use LLMs for this case, the default configuration, model choice is laughably flawed. This LLM can’t be trusted as it doesn’t even know what it is reading.
The correct solution is either advanced OCR with keyword ranking with a basic filter or a far stronger LLM that excels at document / vision parsing benchmarks with an experienced person making the final judgement call in case the technology misses a critical detail.
Rather than using this less accurate one that hallucinates out its decision depending on a dice roll.
That would fail to meet the objective of reducing the costs of hiring an experienced person - the entire point of outsourcing to a chatbot.
Speculative thought only, of course.
But the big question I want to know is "Why did I score that?" And these slop machines absolutely cannot explain anything. That's the root problem with LLMs as a whole. There is no way to describe WHY an llm makes a decision.
Was it because they are a woman? Does the woman's name have more pregnancies than other names? Was it because their job history make the person older (over 40)? Is the person black or black name? Is the name or address attributed to higher criminal tendencies?
But no, you font get to know ANY of that. Slop machine says 66/100 , if you're lucky to even get a number. Usually its a 30 second rejection, or rejection at GMT 0:00 when the batch is processed and you summarily failed.
Hmm, well, maybe a bit with a nuance of elite class structure reproduction (that doesn’t prevent a few transclass to showcase in case anyone critic the perfect meritocracy at run), that’s basically what people get, so crude truth but truth nonetheless.
Oh don’t take it personally. Your own bespoke hand-tailored process of course is different, it does give the opportunity to everyone to reach the most accomplished version of themselves beyond what they ever dare to dream.
It won’t help though with the systematic failure of aiming to provide an accessible path to flourish for everyone and letting no one behind.
Again, this is no fault of any specific player, but as long as a majority feel compelled to move within the frame of the game with few winners that merit all they got in contrast to large stock of inept losers, the outcomes are no wonder.
There's no better feeling than building something open source and watching it take off. Nine months ago, I built a simple hiring agent to solve one very real problem.
Things it is not: It's not an ATS. We don't use it to screen our open roles. Our customers don't use it either.
Here's what it is: Every year at HackerRank, we get 50,000 to 60,000 intern applications. No human can read that many resumes well. So I built something to rank them, helping me decide which resumes to read first.
[This was before we built AI Interviewer (Chakra) to automate the first round of interviews, so candidates are no longer rejected based on their resumes alone.]
Two things worth clarifying since I've seen them come up in this thread:
The default model is gemma3:4b because it's what runs locally on most laptops - no cloud API needed. Actual resumes are evaluated using a top Gemini model. The repo ships with a demo config, not the production one.
The cutoff score was set very low — the system was designed to rank resumes, not reject them. Only resumes at the very bottom of the distribution were filtered out. The vast majority passed through to human review, where the real decisions were made.
Over the last week, it's taken on a life of its own. People are cloning it, running their own resumes through it, opening issues, sending PRs.
I contributed to open source a lot in college. Somewhere along the way, I drifted away from it. This week reminded me how good that feeling is. This thread has also given me more ideas than I expected. The critiques here are sharp and I'm already thinking about how to act on them. Improvements are coming.
I'm not sure if your intent was to come across as having written this yourself, but it did not have the effect of improving my perception that this approach is flawed.
I was also disappointed that you didn't address the variability in scores. I'm inferring that you believe the larger model takes care of the main observation in the post, but I don't really see you directly addressing the points.
Maybe it's just me.
Reading this thread, I'm hoping to minimize the variability even further (even though I know it can't be fully removed).
Or are you using it to screen? I'm confused.