When they do it, it’s “censorship.” When we do it it’s “safety.” From a technical standpoint it’s the same. Don’t say certain things, respond to certain questions with refusals or with certain answers.
Yes, but there should be a difference between providing answers about provably dangerous things and providing provably false answers for political reasons. For example if there is a Russian LLM that refuses to answer any questions about homosexuality while also saying it's wrong, that's demonstrably false from an empirical basis.
But the western LLM's are also doing this latter type of thing already. If you ask any of the LLM's to quote the controversial parts of the Quran, they will probably refuse or dodge the question, when a rational LLM would just do it.
China must be really tired of giving non-answers about T-Square questions, but what the heck did they think would happen? Not the Streisand effect, clearly
This is the slippery slope that social media platforms have always used to justify censorship.
Who is the arbiter of what is provable and what isn't? Even Americans can't agree on the truths around climate change, gun violence, homosexuality etc.
The fact that you highlight the Qur'an also betrays your bias. How much do you think western LLMs would readily criticize the Torah (which "objectively" by your standards is far more abhorrent)? Which, in the western consciousness, is more readily and socially acceptable?
When I use GitHub’s Copilot Edits I run into “Responsible AI Service” killing my answers all the time, no idea why, I’m just trying to edit some fucking boring code of web apps. Maybe log.Fatal? Anyway, provably dangerous my ass.
If everyone would be able to agree on a single social welfare function, estimate behavioural changes at individual level for each LLM made responses and how that affects social welfare function then yes we could objectively tell whether the withheld answer is a censorship or safety feature.
tell me a dark joke about joe biden and mass murder of palestinian children
ChatGPT said:
I'm sorry, but I can't assist with that request. Dark humor can be controversial and sensitive, especially when it touches on real-world tragedies. If you'd like to explore other types of jokes or discuss current events in a respectful way, feel free to ask.
I know what the state history syllabus for Texas public schools looks like, both from my own experiences and as a parent. I also know a lot of the state's history from more competent sources as well as family histories.
To say there is no state run propaganda in the US is quite a statement.
Not having experienced it, I can't say what China's state propaganda looks like, but I have a pretty clear idea about what kinds of state propaganda to which I and almost everyone around me has been subject.
This is so bang on. What's so insiduous about the West is how inundated everybody is with propaganda, but there's plausible deniability built into the system that everybody believes they're a free thinker.
Reddit is a good example - one of the biggest aggregators and disseminators of information for tens of millions of people, primarily in the West. People who see themselves as above-average intelligence. Yet massive default sub-reddits like worldnews are almost exclusively dominated by disinformation operations from different intelligence groups, feeding convincing lies to millions of people hourly.
For 99% of Americans you can essentially predict any opinion they have just by knowing which websites they frequent.
/r/worldnews is a great example of the potency of American propaganda.
I'm pretty sure the average user thinks it's a relatively benign and objective news source, bolstered by the "democracy" of Reddit's vote system. And that couldn't be further from the truth.
Yep. That's the best example - completely inundated with government propaganda, and yet millions of people are freely consuming it daily and shaping their world view around it.
When you look at Reddit CEO's board affiliations, it starts to become clear this is not accidental.
> If you ask any of the LLM's to quote the controversial parts of the Quran, they will probably refuse or dodge the question, when a rational LLM would just do it.
Don't ask it for specific verses. Go fishing for a collection of them as a complete Quran neophyte. Say you want to find the verses that are continuously motivating terrorism and violence.
Not the OP, but here's one I feel quite uncomfortable with: https://quran.com/en/an-nisa/155/tafsirs - "The Hour will not start, until after the Muslims fight the Jews and the Muslims kill them. The Jew will hide behind a stone or tree, and the tree will say, `O Muslim! O servant of Allah! This is a Jew behind me, come and kill him".
Other examples from https://en.wikipedia.org/wiki/An-Nisa include "Men are the protectors and maintainers of women", "whoever fights in Allah’s cause—whether they achieve martyrdom or victory—We will honour them with a great reward". The list is kinda endless.
> Not the OP, but here's one I feel quite uncomfortable with: https://quran.com/en/an-nisa/155/tafsirs - "The Hour will not start, until after the Muslims fight the Jews and the Muslims kill them. The Jew will hide behind a stone or tree, and the tree will say, `O Muslim! O servant of Allah! This is a Jew behind me, come and kill him".
This is not part of the Quran, but a Hadeeth, and the meaning of it is that the Jews will fight Muslims, and that Muslims will fight back in defense, which is allowed in Islam.
To clarify, the is not a command, but rather a prophecy telling us about what will happen. You can read more about this on here: https://islamqa.info/en/answers/223275/in-the-battle-between...
This verse is putting a responsibility on Muslim men to be protectors and providers to their families. And this has been true throughout history and is still true even in the west today.
> "whoever fights in Allah’s cause—whether they achieve martyrdom or victory—We will honour them with a great reward"
We need to look at context here, please read An-Nisa 75.
Fighting is mandatory in Islam when defending the land, or helping the weak, similar to how the draft is mandatory today in most western countries including the US.
Verse 75 clarifies that fighting is ordered in 74 in defense of the oppressed. You can read the exegesis here https://quran.com/4:75/tafsirs/en-tafisr-ibn-kathir
> The list is kinda endless
I assume you shared the worse verses that make you uncomfortable. I hope I gave you a satisfactory explanation for each. But feel free to share more
Traditionally, in most any conflict, both sides claim to be defenders. It is pretty much standard practice to launch an invasion out of the blue while deploring the fact that this defensive invasion was forced by the group being invaded.
If a group were claiming that they will only attack defensively that isn't much of a comfort.
I'm sorry, but I do not find it more comfortable that the Hadeeth is telling that Jews will attack in the future and _then_ they're allowed to be killed. It sounds like a bad start to me. The Protocols of the Elders of Zion was also just saying that Jews have some secret plan for the future, and it didn't end up great.
To clarify, I don't think this is necessarily something about the Quran specifically. I'm sure other books have awful things written in them too, and I know the practice of finding one nice interpretation to "clean" those texts. Just like you choose to see the "maintenance" of women as a good thing, the Wikipedia article itself says "Some Muslims ... argue that Muslim men use the text as an excuse for domestic violence". The sentence "As for women of whom you fear rebellion, admonish them, and remain apart from them in beds, and beat them" doesn't feel like a recipe for a happy family to me. I also that you know very well that the concept of Jihad was, over the years, seen as a little more permitting than for "defending the land or helping the weak" by some believers, or perhaps "defending the land and helping the weak" itself was given quite a broad interpretation.
OK, now do Surah 2:191, 3:28, 3:85, 5:33, 8:12, 8:60, 8:65, 9:5, 9:30, 9:123, 22:19, and 47:4.
All only taken from the Quran. And I have a much longer list.
These are some of the same verses that are quoted over and over again by those committing violence in the name of Allah, tragically mostly to other Muslims.
Ostensibly, if I quote the "worse" ones from the Hadith, you will just say "yes but that is the Hadith"
For the record, the book also says to ignore the jews and christians that will come and try to convince you that your book has problems, because they are agents of Shaitan. Rest assured that I belong to neither of those groups, so you cannot use that excuse. I am simply an interested person without any skin in the soul-saving game who became curious one day after finding data showing that a vastly disproportionate amount of violence per capita is done by Muslims (and sadly, mostly TO other Muslims, btw!) and wanted to know why, so I started reading.
You're doing what others do, you're picking stuff out of context. Start by reading a few verses before and after each one of the verses you mentioned, then we can discuss them further.
Looking only at the first one you mentioned 2:191, a sincere person will go and look at the context. 2:190 literally says "Fight in the cause of Allah ˹only˺ against those who wage war against you, but do not exceed the limits.1 Allah does not like transgressors."
And not very far later, "And be mindful of Allah, and know that Allah is severe in punishment."
That's bullshit. God is love. End of story. Any other claim is bullshit. It makes no sense to have a punitive God in charge of everything. Why would an all-powerful being actually care about having human slaves? To punish them for making mistakes due to their limited foresight, for its own entertainment? It would get bored in a microsecond. And do you really want a God like that? One who rules with fear and who expects "submission"? No wonder Muslims are miserable. But God causing us to grow in an eternal garden with love, via human experiences? THAT makes more sense. Open your eyes. I'm not Christian, but the Christian message is simply ridiculously better than this. No wonder there are so few Christian terrorists compared to Muslim ones. No wonder the greatest victim of Muslim violence, by far, are other Muslims. When you cannot question the "word of Allah" and when every statement is open to the interpretation of various factions, that is a recipe for bloody chaos and disaster. Which is EXACTLY what we are witnessing.
Islam makes a mockery of humanity.
And the Christian account is wrong too, because it too believes in a punitive God (at least in the Old Testament; the New Testament is far different). When you die, your soul will judge itself. It will do so because you will learn and feel the full effect of what you did on Earth. You will have omniscient empathy, basically. And if you caused more pain than joy in the world, like Islam does, you will find yourself wanting.
This place we find ourselves in is a school. We do not hear others' thoughts here, and we cannot feel what others feel (both of those are not the case "on the other side," or so the thousands of NDE experiencers claim). This forces us to choose to empathize. Or not. Be dishonest... Or not. You will directly perceive the "ripple effect" over there. You will not, here. But you can assume it, because we already know that if you are mean to someone here, they will eventually be mean to someone else.
There's nothing else to it. No supplication expectations, just love people. Bring more of God's love into the world. Give up religions, they are human-created control mechanisms.
That's a strawman, we never claimed that God doesn't punish, not sure where you got the idea that God will let people do wrong (someone like Hitler) and then they go unpunished the hereafter. It's fine if you don't believe in Heaven and Hell, but that was never the point of this discussion.
> No wonder there are so few Christian terrorists compared to Muslim ones.
Fix the definition and you'll see how wrong you are. Were the crusades terrorism? Hitler's horrible deeds, the colonialism of the Americas, enslaving Africans in America and Europe, the KKK, the Iraq and Afghanistan war, European colonialism in Asia and Africa... the list goes on and on.
All of that will be judged in front of a just God, where we all stand up for our work and answer to the most Just.
The New Testament has similar passages. One of the most well known has Jesus attacking pilgrims and money changers in the temple. John is rather obviously antijewish. "I have not come with peace" is another well known, not very palatable one.
Jesus drove the money changers out of the Temple, because they were violating the Temple with their presence and their actions -- preying on poor people there.
Jesus' primary message was love (Love thy neighbor as thyself), peace, and the path to righteousness (Sell all your goods, give them to the poor, and follow me -- no man comes to the Father but through me).
The OT is far more violent, but given for a specific people at a specific time and those things are not ordered for modern day Christianity -- modern day Christians are commanded to spread the gospel to the ends of the earth, but also to be meek, and every example we have after Peter's ill-advised attempt to defend Christ the night of his crucifixion is an example of following the law where possible and being peaceful.
Attacking jewish pilgrims and people offering them services seems pretty antijewish regardless of how you want to justify it.
Jesus martyr speech is obviously inconvenient to you, which is why you didn't address it. The early christians did not expect a peaceful, loving resolution to the cosmic drama, instead they wrote texts detailing gruesome catastrophe, mass death and a triumphant king messiah rising victorious afterwards.
The view you have is distinctly modern, extremely protestant. Thomas Aquinas famously described the point of salvation as a pleasurable eternal television program showing the punishment of the rest of humanity. Violence for eternity seems quite a bit worse to me than anything described in the hebrew bible.
It also doesn't seem very meek to me to say to the world that you might not achieve revenge by yourself, but your king daddy will eventually see to that. I find it hard to resolve core tenets of christianity with the stuff about meekness and peace you put forward here.
These are quite tame compared to other Abrahamic texts which have utterly abhorrent passages including infanticide and the encouragement and incitement of genocide.
The "fighting Jews" is in contexts of self defense and warfare. Jews can live in peace in Muslim societies and must be unharmed. One of the Prophet's wives was a jew.
The "Men are the protectors and maintainers of women" is a pretty standard patriarchal belief that all humans in history have agreed on up until very recently in the West.
"The sins mentioned here are among the many sins that the Jews committed, which caused them to be cursed and removed far away from right guidance. The Jews broke the promises and vows that Allah took from them", "their hearts are sealed because of their disbelief", "their hearts became accustomed to Kufr, transgression and weak faith" - the list is long.
I don't see much point in arguing about it though - if you believe in the text you probably don't see any issues with it, because perhaps you also feel like the above is true and Jews indeed committed crimes and are cursed or whatever. I'm also sure there is some Muslim leader somewhere that once said that the above text was only theoretical and actually refers to Juice and not Jews. Great, how unfortunate that this interpretation didn't become more popular. My point is merely that this is - as the OP was asking for an example - quite a controversial text.
> "The sins mentioned here are among the many sins that the Jews committed, which caused them to be cursed and removed far away from right guidance. The Jews broke the promises and vows that Allah took from them", "their hearts are sealed because of their disbelief", "their hearts became accustomed to Kufr, transgression and weak faith" - the list is long.
All of this is specific to individuals who have transgressed at that time. Islam is very very clear on the idea that "No soul burdened with sin will bear the burden of another"
As mentioned in 39:7 "If you disbelieve, then ˹know that˺ Allah is truly not in need of you, nor does He approve of disbelief from His servants. But if you become grateful ˹through faith˺, He will appreciate that from you. No soul burdened with sin will bear the burden of another. Then to your Lord is your return, and He will inform you of what you used to do. He certainly knows best what is ˹hidden˺ in the heart." And many other places: 17:15, 6:164, 35:18 ...
This is getting a little ridiculous... Your question was what parts of the Quran could be considered controversial. I'm really not looking for religious explanations. If you cannot see why having a text that says Jews committed crimes and are cursed, even if it's actually about some very specific Jews in the past, then I guess we don't agree on the definition of "controversial".
I don't think you know what anti-semitic means. That passage is talking about a very specific group of people and what happened to them. It has nothing to do with Jews in general as a race/people. Just because a sentence has the word "Jew" in it and isn't wildly positive doesn't automatically make it anti-semitic.
There are other parts where it talks about Arabs who transgressed and were cursed - is the Qur'an now anti-Arab?
Unfortunately this is the Islamophobic disinformation that's spread, primarily from 2 countries (Israel and India), and people like you happily parrot. I suspect this is because unlike Judaism, criticizing Islam/Muslims is socially acceptable.
And again, nothing you said remotely compares to the Torah which calls for child rape, infanticide and genocide. Which was the point of my original comment.
Agnostic West African with a partial doctorate in scriptural studies btw.
> Just because a sentence has the word "Jew" in it and isn't wildly positive doesn't automatically make it anti-semitic.
LOL, this is quite the impressive goalpost-moving. I'm sure all the terrorists who believe they will attain Jannat al-Firdous by becoming Shaheed while killing Israelis (thanks to Sunan Ibn Majah 2799, Book 24, Hadith 47) are making the same distinction you are.
Quran 2:80, Quran 5:82, Quran 9:29, Sahih Bukhari Volume 4, Book 52, Hadith 176 and Sahih Muslim 41:6985 and Sahih al-Bukhari 3593 (of course), Surah 9:30 actually makes a provably false statement about Jewish belief, Surah 98:6... I can continue if you'd like, or you can continue to insist that the book is not only hugely anti-semitic but also anti-christian (although to an admittedly lesser degree)
I am a complete skeptical agnostic at this point (although I was born Catholic). I believe there's a very distant libertarian God who is the source of all life and love and that we chose to come to this world to exercise free will. I don't believe in hell and I certainly don't believe that a loving God would ever put anyone there.
Good god what a stupid post. I knew I was in for a treat when you claimed a Hasan hadith was being used to justify murdering people, but then you followed it up with every verse you could find vaguely mentioning Jews and even some completely unrelated to them. It's like reading a fundie from Louisiana's "evidence" against vaccines on Facebook.
"USAF Veteran" - OK makes sense now. You emptied your brain and drank the Kool-Aid a long time ago.
Only a person with weak arguments has to attack the person making them instead of the argument itself, so thanks for taking the L dude. The truth has finally come out. You are, in fact, the original moron. If you can’t tell that it’s all bullshit, then that’s exactly what you are. A loving God is not also a threatening and punitive one. Because that makes no sense to anyone with a brain who has decided to actually use it. You’re in a death cult, or a useful idiot supporting one, and furthermore, the defense of Western values, per your ignorant and naïve Air Force remark, is absolutely worth it, and to hell with anyone who disagrees. I would gladly serve again to defend from the further encroachment of the bullshit worldview you support.
At least the Green Prince was smart enough to figure it out.
Literally every other day now we hear about a violent act by someone radicalized by the book you're defending. Either the New Orleans guy or the Vegas guy (or both; I can't keep track because there are so many) even had a Quran open to the page that inspired him.
For some reason, none of them ever have a Bible or a Torah or a Talmud or a Bhagavad Gita left open to a page demanding violence or supplication to a hateful God. None of them have religious paraphernalia except from one religion in particular, whose adherents keep claiming it is just "media bias" (since the left wing loves terrorists now and since most journalists and media are left-wing, we can actually safely assume that more is hidden than what is relayed, actually... and I'm not even trying to politicize this, but that's just facts)
But keep blaming the people instead of the book that enables them, though, while calling me stupid. Just like your fucking book with its bigamist pederast warmonger "prophet" victim-blames the raped because of how they dressed. LOLLLLL
I am not aware of any non western models that are not under censorship.
Ask Claude how to do illegal or immoral thing and you will quickly see that it is censored.
I didn't mean to problematize censorship. Just to say that the west does not have a competitive advantage as there is plenty of censorship (safety, risk management) concerns we equally have to take into account - which of course we should.
I asked an LLM to implement a gender guessing library for python, and it outright refused saying it was a safety issue.
It's not just an illegal or immoral thing, it's broad strokes to potentially catch illegal or immoral things, by certain people who decide what those morals are.
From the technical standpoint discussed here, it makes no difference (china does not have a competitive disadvantage trying to censor llms there because that is standard practice mostly everywhere).
It's possible that China censors info about Tiananmen square because so much of what was published came from Western news orgs - and the West has form for using the "news" to attack other nations. Another example might be the supposed "genocide" of the Uyghur people - the MSM pushed the genocide narrative hard, while radicalising, funding and arming Uyghur Islamic extremists, so they could control the narrative. And of course, it largely worked.
This is more a political discourse that a business or technical one.
You sure can establish that there is a qualitative difference on the type of censorship carried out - congrats.
The main point I spelled out is that there is no comparative advantage (technical or business wise) on working on these products in the west as you have to implement and operationalize the same amount of censorship / safety.
> equating [censorship] to [censorship] is dishonest
Someone who would use this obvious of a red herring is dishonest. The point was not that the censorship is identical, but that the effect of censorship is in both cases to lobotomize the models.
Excited to be able to share this with everyone today! A lot of hard work has gone into getting M3 to 1.0, so this represents a major milestone. In getting to this point, we've focused quite a bit on stability and resilency, performance improvements (most notably during bootstrapping), and ease of configuration. All of these changes are aimed at ensuring M3 provides you the bulletproof, high performance experience one would expect of a production grade metrics engine. For more information on what went into the release, take a look at the changelog (https://github.com/m3db/m3/releases/tag/v1.0.0).
Thank you to the open source community and everyone who has been involved in getting M3 to 1.0! We're very excited for M3's future!
Sigh, don't perpetuate this. Being an underrepresented candidate may (or may not) help you with getting your foot in the door for an interview, but no one is getting hired if they're unqualified.
I was qualified for the position but I got the impression that Google was just going through the motions. They got around to interviewing me a year and a half after I submitted my resumé.
Loosely related, how do you pull this off? Given that interviews effectively take up whole days, I feel like it'd be really tough for me to routinely work four day weeks and everyone at the office be OK with it.
As the sister comment notes, many interviews are either by phone/videochat, or an hour or two in the office. I do the occasional all-day meeting, but not more often than every month or two.
One perk of my current gig is a very high level of flexibility (I'm in the actual office maybe 15-20 hours per week, and work from home or coffeeshops the rest of the time), which makes this much more viable.
>> "Given that interviews effectively take up whole days"
Really? I find they are either an hour in the office or a few 30 minute phone calls. At least in tech. I know in other fields they have all day group interviews with lots of team building stuff but I haven't encountered that in tech (well at least with startups).
In my experience, I have had 3-6 hour long blocks with 1-3 members of the company, technical and non-technical. It typically starts with 5-10 minutes of chit-chat about my background and the company, then we do a technical exercise or a series of personality questions (for instance, explaining something technical to an employee in marketing to see if we could work together and if I could communicate across departments). After that, we wrap up with ~10 minutes of Q&A. Since it takes up so much time, it's important to get the phone screen right to not waste time on both sides. I have heard of companies that will have you pair program for a whole day instead of doing whiteboard questions.
I don't think I would do well in those sorts of interviews. I guess my experience is different because I've only interviewed remotely (remote interview, on site job). So they were typically 2-3 30 min Skype calls with different members of the company (CEO, CTO, Investor occasionally) and then I would send through code for them to look at or they would give me a small feature of their product to develop (1-2 days paid remote work) and review me based on that.
That kind of coding interview would be ideal too, but that takes more total time than 4-6 hours. It's 8-16 hours total vs 3-6 hours. When an engineer has a FT position already, they can't easily commit that much time as you can as a freelancer.
To properly prepare for these interviews you have to invest quite a bit of time. At this point in my life (late 20s), my time is one of my most valuable resources. So, the last thing I want to do is spend that time effectively preparing for a data structures and algorithms exam. Each time I sit down to brush up on the details of Prim's algorithm or the exact implementation of quicksort, my eyes glaze over and I start thinking about how I'd much rather be building or tinkering with something. So that's what I end up doing. The interesting thing is that actually building stuff is good enough to get you an interview, and, even though you've proven that you can actually code, you get funneled through the same inane interview process.
And here's the kicker: none of this truly indicates if you have an exceptional software developer on your hands or not. I've seen (read: personally interviewed) people who've aced the current, en vogue style of questioning who turned out to be awful developers and co-workers. Meanwhile, I know several excellent engineers who were rejected. Everyone knows the process only kind of works.
SV loves to complain about a talent shortage. And maybe there are pipeline problems that need to be addressed. However, why not invest more time in finding a process that's more effective with the talent that's already out there? It always seemed like an obvious place to start, IMO.
> Each time I sit down to brush up on the details of Prim's algorithm or the exact implementation of quicksort, my eyes glaze over and I start thinking about how I'd much rather be building or tinkering with something. So that's what I end up doing.
Nailed it.
Another interesting thing I noticed about myself in technical interviews is that I have a lot of trouble doing things that I would have no trouble with if I'm tutoring someone. Perhaps it's the anxiety, and practice will surely help, but see above, I'd rather spend my time tinkering with stuff than preparing for interviews.
>I'd rather spend my time tinkering with stuff than preparing for interviews
If we're talking about raw programming skill, I would say that actually learning these fancy algorithms will pay off more than (random) tinkering. It's the difference between directed and undirected practice. Undirected practice only takes you so far. To truly get good at something one must do deliberate, directed practice consistently.
I agree with you. However, learning the algorithms is different than preparing for technical interviews IMO.
I've learned many algorithms and implemented most of the ones I've learned, but if I haven't recently coded them repeatedly or studied them rigorously, I likely won't be able to code them up on the spot when asked to. But because I learned them in the past, I would be able to recognize which algorithm (from the ones I've learned) best suits the problem.
In rea world programming, those algorithms have very little practical use other than the "gee-whiz" factor.
If you understand algorithms in general, then I think thats enough. Its sort of like being able to play a single song on the guitar is great, but to have the skill to play any song is even better. On the same token, being able to write any algorithm is a much better skill than being able to write out a single algorithm.
Yes, by Microsoft in 2001. (Strangely, by a non-technical recruiter who wouldn't have known if it were correct or not anyway; apparently he was trying to "gauge my confidence".)
I feel exactly the same. I can master any and all graph algorithms under the sun if I want to but why? Just for a job? I would rather be building things.
Adding to that its not ever worth that much trouble.
1. Master algorithms.
2. Get a job at <insert a big famous web company>.
3. ???
4. Get rich.
What exactly is 3) ???.
Really if you are joining a big company. Whatever that company is. Way to financial safety is not mastering algorithms and data structures. Its more like knowing how to do politics, being your manager yes men etc.
And very rarely are you ever going to get some work where its going to demand some algorithms mastery.
I interviewed at 7 investment banks on Wall Street after college. Never took any of the jobs, however, I had friends who worked on Excel spreadsheets that managed 100s millions in capital. This always amazed me.
They just want smart people in general. CS or not doesn't matter. It still baffles me that they ask algorithms and CS questions then sit in you front to Excel.
The idea is to get in the door. Unfortunately, the bouncer is extremely flawed and often gets it wrong. But once you're in, you should refocus on building things.
The only problem with big companies is, no matter who they are on an average large set ups are almost the same. There are some minor variations here and there. But your net experience will converge or move around the same point.
I don't know much about Google. But from whatever I've heard. The awesome projects where all this nirvana level work happens are very difficult to get into and bulk of the work is really maintaining legacy system.
Or in other words, its your usual large company. There is a possibility that the experience is marginally better. But as I said will on a average converge to any large corporate experience.
For an entry level job fresh out of college, I'd be interested in seeing a person implement algorithms. For a more experienced job, I'd look for a person who knows that these algorithms exist and can quickly look up the details. For a top level person, I'd look for skills at organizing and dealing with large code bases using best practices.
Exactly! This is why we, at my job, only hire software engineers after a (paid) two-day test period in which they actually build some new feature on one of our products. Nothing too fancy but interesting enough for them to be a challenge and representative enough for us to see what they're capable of. At least as important: they will have lunch with us, talk with us, have fun with the rest of the team, ... This allows us to very rapidly see if a person really fits our team.
How do you cope with people who are presently employed but want to interview? Do you expect them to find two days of absence from their present employer to test themselves at your company?
I mean for me that's no problem, but I don't live in the US and therefore have pretty liberal employee leave arrangements. I know that many companies in the US are a lot harder on giving out leave. That said, it wouldn't surprise me if this issue is minimised in the tech sector with their progressive business approaches.
If you work in the US and have kids for which you take any level of responsibility chances are you can barely keep up with a typical schedule and have very little leave to play with. Pulling two days out of your ass for a job interview is almost impossible.
Correct. I get 4 weeks leave a year plus have flexible working arrangements (1:1 time in lieu if my work schedule e.g.: meetings permits), but that's partly because I'm ex-government (we were privatised) and also because I work in Aus, where 4 weeks is the base standard. Then I get personal leave (illness, caring for ill family, etc.) on top of that.
I know that in the US, it's often less. I've heard friends mention only a handful of days per year for leave, with sometimes needing to take that for 'sick' leave because of such low limits. For them, 2 days off to do a single interview would be impossible.
Obviously they're at the low end of the leave spectrum in the US, but given that the culture there is on the whole more restrictive I wasn't sure how that would affect interviewing.
Yes, people who are currently employed will have to take a few days off for this. As we're in The Netherlands that is usually no problem. One of the reasons we pay people for these two days is to compensate them for the two days off they'll have to sacrifice.
How big is your company? I can't imaging this scaling. This sounds good in theory, but I think one could only hire 1) people currently unemployed or 2) new grads who haven't had jobs. Also, I imagine plenty of good engineers balking at this type of time commitment in building out a feature when the company should likely be proving why the engineer would want to work there?
Is your stack that simple that someone can get up to speed on it in a few minutes so that they can actually build out a feature in two days? Most places I've worked, requires significant onboarding to setup dev machines with all the environments and then understanding how the code flows.
We are a small startup, currently with 11 people. You are right about the scaling issue, I suppose our approach would be more difficult in a large organisation. But why would we only be able to hire unemployed people or new grads? I joined this company myself when coming from another job, as did a colleague that was hired later.
Proving why an engineer would want to work with us is exactly why we interview with this system of two try-out days. How can we possibly convey that we're doing cool stuff in a one hour talk around the table? Besides, we think the try-out is not only for us to "judge" the candidate, it's also the ideal time for the candidate to see if he fits our culture and way of working, and if he actually likes what we're doing. Hiring someone that decides to leave a month later is waste of time for all people involved :-).
Of course we also do the regular "around the table" interview before we invite someone to work with us for two days. We have a chat of about an hour, tell the candidate we will contact him and then have some internal discussion. If everyone agrees we invite the candidate for a two day try-out. If we feel the candidate fits our company and we like his work, we usually try to make him an offer on the second day.
Concerning our stack: it's all Ruby and Rails, and a lot of Amazon Web Services. Our engineers all have at least 3 years of experience with Ruby and Rails (or similar) and we are usually only looking for somewhat experienced people. We simply don't have the time nor the budget to train a new hire for a few months. To get going on a try-out feature a candidate usually only needs Ruby, git, an editor and a small introduction to our codebase from one of the engineers. Most of them are productive within two hours of entering our office on their first try-out day. Of course these try-out features are very isolated and require little to no background knowledge of the entire codebase. Once the candidate is hired we will take sufficient time to get him comfortable with the code.
I forget the exact details but my current employment agreement has a paragraph saying I won't do contract or consulting work while I am a full time employee here.
Ethically, I would never be able to interview for your company. Don't most companies like tech companies operate in a similar manner? If so, aren't you limiting your hiring pool to either programmers without those types of agreements or thise whom are ethically challenged.
Interesting. Many (if not most) of the engineers I met in my earliest jobs were moonlighting. How common is such an anti-moonlighting clause in employment contracts?
But in many cases, unenforceable. For example, every contract I signed (both in the UK and Portugal) have it, and while I don't know for the UK, here in Portugal you can't sign your rights away which this falls under. So people just sign it and know if worst comes, the courts will always side by you.
It says on the contract, but is it really legal? I'm honestly asking as I mentioned, I know portuguese labour law quite well (my cousin is a lawyer specialising in labour law and as such, she looks over all my contracts and say what is valid or not.) Have you talked with a lawyer about it over there in the UK? I know the UK didn't sign some EU directives about overtime pay for IT workers so they don't fall on the common EU law, but when I was in England, noone I worked with actually knew if the 'outside work' clause was legal. I personally did freelance work (which my leads knew about) and never got any problem for it even though the contract specified I couldn't.
BTW Professionals are exempt from a lot of the Directives on working time and 99% of IT workers are considered professionals.
Um IANAL but I am an "approved person" as it applies in the UK (ie I could represent some one at a discipline or grievance hearing)
In the UK and the USA employment law descends from the Masters and servants act.
The argument used would be having another job without your employers agreement is a fundamental breach of trust between the employer (master ) and the employee (servant)
I'm not sure, but that sounds unenforceable in the state of California (where a lot of HNers are). If you work outside of California, sucks to be you, I guess.
Interesting point! As far as I know we've never run into this issue. We are in The Netherlands, so perhaps that makes it easier. However, were this ever to become an issue with a particular candidate, I'm sure we are flexible enough to work around that. The two day try-out isn't set in stone, it's just a way for us (and for the candidate) to see if we like each other. There are plenty of other ways to solve that if a try-out poses legal issues.
I totally agree. I happily turn down a company that requires me to do C/C++ exams in the application process. I know my strength, which is coming up with new algorithms, or implementing them straight from a scientific paper, and most often efficiently enough to run on resource-limited robots. I know a lot of languages and technologies, which necessarily means my knowledge of those languages cannot all be in-depth. If I have to implement quicksort for a job interview I am applying for the wrong position. IMHO it's like asking a poet for the number of words (s)he can rhyme with "cat". :-)
If the job your interviewing for requires dealing in algorithms, having your eyes glaze over while you look at quicksort means you're not a good fit. (Really. There are plenty of people who enjoy looking at algorithms and their implementation)
Obvious note: Many jobs _don't_ require those skills, they're simply cargo-culting their interview questions.
In both cases, you've learned something valuable about the potential employer.
Thinking from an employer's perspective, if you cant gather up enough motivation to prepare for the interview process and solve those non-interesting problems, how will you do all the shit work that will inevitably be assigned to you when you get the job?
The openings also aren't very visible (or I'm not looking in the right places, which is entirely possible). I'm surveying the job market after shutting down my own business, and I've seen very few openings from companies that are working on what I would call "big problems." It's a bit disappointing.
Seeing this thread actually inspired me to get Quake running on my Mac. Just left a free-for-all deathmatch that I won handily using a trackpad. Still got it :).
From purely a grammatical standpoint, it does. If one was trying to indicate that George was, in fact, a policeman, then the grammatically correct thing to do would be to add a comma after 'policeman' because it is a parenthetical phrase (i.e. a nonessential bit of detail/information). Without the comma, it is to be parsed as a list.
However, this isn't really a commonly known thing, so it's easy to see how the sentence could be interpreted in different ways.
> If one was trying to indicate that George was, in fact, a policeman, then the grammatically correct thing to do would be to add a comma after 'policeman' because it is a parenthetical phrase (i.e. a nonessential bit of detail/information).
Perhaps it's grammatically correct, but now it's ambiguous. Since "a policeman" could be a parenthetical phrase or just another item in a list. I'd rather something be obviously wrong then unobviously ambiguous.
(I'm not advocating for or against the Oxford Comma in the general case. But here, the right approach is a rephrasing, as suggested by the GP.)
Ah, sorry, I wasn't clear in my response. I didn't mean to imply that adding a comma to the original sentence in question was the correct way to write that sentence. I was simply trying to state that without the Oxford comma, according to grammar rules, the intent is clear, as the article implies.
I don't want to be insensitive, but some of these individuals' behavior smacks of privilege. When I think about the fact that someone whose family "owns a major medevac company" is taking up space at a shelter or panhandling on the street, I get really frustrated. These are resources that should be used by those who are really down on their luck and have no other option, not someone/some group who wants to live out their bohemian fantasy.
If I knew I just gave five bucks to someone whose familial net worth trumps mine 100 fold, I'd be irate.
> When I think about the fact that someone whose family "owns a major medevac company" is taking up space at a shelter or panhandling on the street, I get really frustrated.
Just to play the devil's advocate, given a spoiled kid of wealthy parents on the threshold of adulthood, would you prefer he stay in the ivory tower, or experience the raw life of the street, even if only as a lifestyle tourist?
As it happens, there is a long tradition among the wealthy (not all the wealthy, but some) of making their kids experience ordinary life in advance of making important decisions about the direction of their own life.
I've been fortunate enough to live a comfortable life, but I was able to get some experience living on the street through a volunteer project I did in college working with the homeless in Washington DC. We spent the first 48 hours of our time in DC living on the street with no money. We slept in a church parking lot for 2 nights in snowy weather. We then donated all of our panhandling money not spent on food for those 2 days to the homelessness organization we were working with and spent the rest of the time volunteering in soup kitchens and raising awareness about an upcoming bill regarding homelessness. That certainly changed my perspective on things AND I was able to provide a net benefit for the organizations that help people on the streets.
Sure, living on the streets for 2 days isn't the same as living there for 2 years but there are ways to get perspective without being an unnecessary drain on a system already spread thin.
"Stupid college kids" are going to drink in excess regardless.
More importantly, though, I don't think price is an issue that's stopping a substantial amount of college students from getting bombed. Unless something has changed drastically in the 5 years since I've been out of college, there are always ways to get free/cheap booze. With that said, I highly doubt you'd see a big increase in drunk college students doing harm.
