Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 74. No – 88

danunparsed.com

Post reply on HN
Print view View original

421–430 of 463 posts

Re: HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 74. No – 88

#421

Post by tikhonj »

nonethewiser wrote: post #379
jerf wrote: post #290

Earlier quoted context omitted.

Everything is correlated to everything [1]. 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 fr…

>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. Uhh.. what? No that doesn't follow at all. Screening resumes in a way that correlates to race, gender, etc. is not illegal. This is a fundamen…

The US has a notion of "disparate impact"[1] that means you can be liable for discriminating based on a protected characteristic on the basis of correlation. This is why HR departments are very hesitant to use things like IQ tests for screening candidates, for example.

[1]: https://www.congress.gov/crs-product/IF13057

Re: HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 74. No – 88

#423

Post by mk89 »

At my company someone has introduced an internal tool that should help understand and give a "score" to design documents from teams.

Needless to say, this tool gives scores exactly like the article mentions. Same document, same LLM, same prompt, and different results. It becomes even more ridiculous once you switch to other models, or if you ask a model to review the work of another model.

I am not sure why we insist on making LLMs do the work they are not supposed to do and/or in a way they are not supposed to do.

The worst part is that people are aware of the problem but they just ignore it and consider it as "a reference number, just to have an understanding".

If it were like that, it would be less of a problem. The issue comes from the fact that eventually someone without enough knowledge will trust the output (so X points out of Y is how it is), or someone will stop challenging the output and consider it for their process - like in this unfortunate case of hiring.

At a certain point, people who don't know what they are doing give a tool that doesn't know what its doingto people who don't know what they are doing. A pure mess. And everyone has to comply and applaud. If you go against, you are against AI.

This is what I hate the most about AI. Not the tool, but the shortcuts we're willing to take to justify its existence.

Re: HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 74. No – 88

#424

Post by DiscourseFan »

AnimalMuppet wrote: post #363
DiscourseFan wrote: post #361

Earlier quoted context omitted.

I wouldn't doubt that lawsuits for employment discrimination for any company (and I suppose it was most of them) that used LLMs in hiring processes will become a very lucrative business. They are all open to civil suits at this point.

And, if there aren't enough lawyers to do all that work, you could use AI to file the suits. I'll let you decide whether that's a dream or a nightmare...

I don't see why its a problem to use LLMs to assist with legal work if someone else uses it in a way that exposes them to lawsuits. That's like saying you shouldn't using a ledger to do accounting just because some people cook the books.

Re: HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 74. No – 88

#425

Post by programjames »

12_throw_away wrote: post #393
programjames wrote: post #364

Earlier quoted context omitted.

Nondeterminism is also a feature, not a bug. If you don't want people to optimize against your filtering process, you have to make it somewhat nondeterministic. For example, better candidates are exponentially more likely to pass the filter, instead of a hard cut-off at the top-100. Then it becomes no longer worthwhile to Goodhart the filtering process, because it barely increases your chances and there are so many m…

> If you don't want people to optimize against your filtering process, you have to make it somewhat nondeterministic. I'm sorry, I'm not following this at all. When you say "better candidates are exponentially more likely to pass the filter", we're still are talking about a metric , yes? A metric that can be optimized? Why would switching from a hard cutoff to some sort of stochastic filter weighted by this metric di…

Optimizing for the metric involves:

1. Optimizing for generally applicable skills that the metric is trying to measure.

2. Optimizing adversarially to hill-climb the metric.

You want candidates to do (1) and not (2). You can make them agnostic to the second by setting

    d(expected gain)/d(opportunity cost) = 0
      ==>
    expected gain \propto opportunity cost
It is the case that most metrics are logarithmic: it takes just as much effort to decrease one bit of error as the next bit. So

    log(score) \propto (opportunity cost) \propto expected gain
Thus, for them to be agnostic, you should filter candidates proportional to their log-score on the metric (where 0 is a perfect score). Because generally applicable skills are generally applicable, they will still benefit from improving those, they just no longer benefit from adversarial optimization, unless your score function looks very similar to others who have not adopted this filtering process.

The issue with a hard cutoff is that people near the boundary are extremely incentivized to adversarially optimize, as it is usually cheaper than working on generally applicable skills and actually pays off for them. You see this phenomenon on AoPS where (esp. Californian) students talk about grinding for MATHCOUNTS instead of learning calculus.

Re: HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 74. No – 88

#426

Post by vessenes »

forlorn_mammoth wrote: post #391
vessenes wrote: post #295

Earlier quoted context omitted.

Agreed on the desire for continuous behavior. That said, in a modern LLM, is this hash analogy accurate? I would be surprised if a single letter changed most zero temp force ranked outputs. 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…

"Your are a helpful/less assistant" Give it a try. 4 letter difference. Add a few 100 tokens describing the task, such that the change becomes a tiny fraction of the input. Discontinuities everywhere.

But those are VERY different types of assistant. It is correct behavior that you would get different outputs in this case.

Re: HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 74. No – 88

#427

Post by vessenes »

sobellian wrote: post #407
vessenes wrote: post #295

Earlier quoted context omitted.

Agreed on the desire for continuous behavior. That said, in a modern LLM, is this hash analogy accurate? I would be surprised if a single letter changed most zero temp force ranked outputs. 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…

I don't know about single letters, but single words? "Score this resumé. Applicant: Jim ..." "Score this resumé. Applicant: Greg..." Is it obvious to anyone that these will have the same modal response?

I believe there's some data that they will have different responses if the names signify different cultural / race / gender affiliations. Here be dragons.

Re: HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 74. No – 88

#428

Post by AnimalMuppet »

DiscourseFan wrote: post #424
AnimalMuppet wrote: post #363

Earlier quoted context omitted.

And, if there aren't enough lawyers to do all that work, you could use AI to file the suits. I'll let you decide whether that's a dream or a nightmare...

I don't see why its a problem to use LLMs to assist with legal work if someone else uses it in a way that exposes them to lawsuits. That's like saying you shouldn't using a ledger to do accounting just because some people cook the books.

Because using it to do shoddy work that harms people is the basis for the suit. If you're using it for the lawyering, too, how do you know that it won't do shoddy work in writing the lawsuit - shoddy work that could hurt the client?

Re: HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 74. No – 88

#429

Post by WickyNilliams »

YossarianFrPrez wrote: post #134

Looking at the linked scoring prompt (resume_evaluation_criteria.jinja) [0], I immediately see several red flags that suggest the output won't be reliable. (I'm developing an LLM intensive application where the stakes are high enough that I need the LLM output to be reasonably correct.) [0] https://github.com/interviewstreet/hiring-agent/blob/main/pr ... In no particular order: 1. The prompt is trying to get the syst…

Would it be correct to say you have experience building LLM based workflows like this? I'm guessing so, given by your critiques and suggestions of better approaches. Can you recommend any books/sites/other for learning these kind of dos and donts?

Re: HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 74. No – 88

#430

Post by prime_ursid »

WickyNilliams wrote: post #429
YossarianFrPrez wrote: post #134

Looking at the linked scoring prompt (resume_evaluation_criteria.jinja) [0], I immediately see several red flags that suggest the output won't be reliable. (I'm developing an LLM intensive application where the stakes are high enough that I need the LLM output to be reasonably correct.) [0] https://github.com/interviewstreet/hiring-agent/blob/main/pr ... In no particular order: 1. The prompt is trying to get the syst…

Would it be correct to say you have experience building LLM based workflows like this? I'm guessing so, given by your critiques and suggestions of better approaches. Can you recommend any books/sites/other for learning these kind of dos and donts?

This is a technique called LLM-as-Judge. Well-studied at this point. Here’s a good intro: https://www.evidentlyai.com/llm-guide/llm-as-a-judge

I recommend reading Hamel.dev posts. Here’s an example: https://hamel.dev/blog/posts/evals/

Post reply on HN