I kind of see myself from ten years ago in this blog post! I also obsessively studied Mandarin Chinese in my late teens for the sheer fun of it, before doing a math undergrad. I even wrote comments on Hacker News about it a decade ago: https://news.ycombinator.com/item?id=7622940.
At the time I had seemingly limitless motivation for grinding away on flashcards and other learning materials. My progress was strong and I passed the HSK6 after a year and a half or so of studying, which at the time was the highest level of certification offered. I think they changed the system since and added more levels beyond 6. You can do amazing things if you're dedicated!
Today my Chinese is absolutely unusable, and my views on China have soured to the extent that I don't really want to revive my old skills. My takeaway is that learning one of these languages, the CJK languages, Arabic, or similarly weird languages, is just too much effort and I don't think it's worth it. I clearly had a lot of excess energy at the time that I could've directed towards something better. Knowing Chinese is about as useful as juggling and you might as well get really good at juggling if you're bored. It'll save you a few thousand hours.
My takeaway is that learning one of these languages, the CJK languages, Arabic, or similarly weird languages, is just too much effort and I don't think it's worth it.
An excellent observation, and one that also applies to pretty much any skill with a steep learning curve (but whose applicability in one's daily life is decidedly optional -- like learning to play an instrument reasonably well, for example). If you're only doing it "for the sheer fun of it", or as boredom reduction tool then it almost certainly isn't going to be worth it.
On a more encouraging note -- while your Mandarin has evidently atrophied, it probably isn't completely gone. It's just gone to sleep. Language skills have a way of doing that (even one's native language, if one spends a sufficient amount of time immersed in other environments).
But most likely it's still there, and if you ever took it up again, you'd be surprised at how quickly it comes roaring back.
Something similar happened to me -- did intensive Mandarin study in college followed by a summer in Beijing being totally immersed. Was incredible. Then continued with a language course back home, and watched as my vocabulary shrank -- something like 4 hrs/wk. of class (with homework on top) couldn't even maintain my Mandarin, much less improve it. Today I can't understand a thing -- I've literally forgotten it all except for counting to ten and some basic phrases. In hindsight, it was utterly wasted effort, except for the cultural benefits of the summer abroad.
In contrast, I can understand and get by in French and Spanish and Italian just fine, despite having studied those far less. If I'm traveling somewhere I just do a quick review of verb conjugations beforehand. But they just share so many cognates with English. When television is télévision or televisión or televisione it's just not that hard. But when television is diànshì, and virtually every word is brand-new like that... it's just not worth it.
(And even when you learn a new word in e.g. Spanish that's totally different from English, you'll often get it "for free" in another one -- e.g. "pretend" is fingir in Spanish, and fingere in Italian.)
I know a bit of Italian and I found out that if I think hard enough there are cognates! Or, at least, something close to it anyway. I used your example of fingir/fingere and asked ChatGPT. See for yourself:
Me:
Is there a word in English that looks like fingir and is related to "to imagine"?
ChatGPT:
The English word "feign" is related to the Spanish word "fingir." Both words share a common Latin root, fingere, meaning "to shape" or "to form." While "feign" often means pretending or giving a false appearance, it can be connected to "imagine" in the sense of fabricating or creating a scenario in the mind. So, "feign" might be what you're looking for!
I found learning Latin (and to some extent, ancient Greek) to be far more useful for learning new words in the Romance languages (and English) in general than actually learning the Romance languages themselves.
Instead of seeing it as a massive grind, you could integrate it into your life in small ways e.g. conversing with native speakers, reading some of your daily content in Chinese, etc. You'd get the skill back essentially for free, and enjoy it more.
This is nuts, if i learned Mandarin, i would probably move to Taiwan, where the CoL is almost 1/4th of where I am right now. I know some other languages, but loss the will to study anymore lol.
I'm a foreigner who's live in Taiwan over the past four years. You can move here tomorrow if you want :D. You can survive with English (though your life will be easier with Mandarin), and there are plenty of English teachers who never learned Mandarin who've lived here for 10+ years.
Highly recommend living here. I met my wife here. Life's chill. Nobody steals. If you've made at least $60k in salary at least once in the last three years you can apply for a Taiwan Gold Card (kinda like a Taiwanese O1 Visa) and come live/work here very easily.
The main reason I continue to learn Mandarin is because my mother in law speaks zero English, so it just makes everyone's live's more fun and pleasant if I speak some Mandarin. :D
Interesting. I had the impression that Chinese will likely become very useful during our lifetimes... With the momentum their economy has, I expect knowledge of both English and Chinese to become a very sought out skill
There was a soviet era joke: optimists practise their english, pessimists practise their chinese, and realists practise stripping their Kalashnikovs.
Four decades later: I guess some fraction of the optimists have emigrated; the pessimists might be finding their language skills freshly in demand; and the realists teach their grandchildren: https://www.youtube.com/watch?v=fE3UUbBKDS8
> There was a soviet era joke: optimists practise their english, pessimists practise their chinese, and realists practise stripping their Kalashnikovs.
Hah, that joke is more widespread than I realised. The Czech version is that optimists learn English, pessimists learn Russian, and realists learn marksmanship.
- hundreds of thousands run away after the Ukraine invasion to not get drafted (learning English was probably very useful for that, lingua franca of business and generally of the world)
-China is looking to make Russia their puppet state / due to embargo Russians cannot buy stuff from the West, so they try to get stuff via China (on a side note, they also get embargoed there to some degree + this comes at a cost)
-the poor are conscripted to die charging with their Kalashnikov against artillery. What's the expected life of them? 1 day?
Without picking sides, but Russia does not have forced conscription. Ukraine does on the other hand force people via the notorious TCC. Russia is not a puppet state of China. Their relation isnt very strong. Naturally they dont get along with each other. But they are both forced to stick together and form a block against the west. Did you know that most Russians learn english on school?
Except that lots of Chinese already speak English, and their Chinese is better, so I don't ever see a large market for mandarin skills in non-native speakers on the same scale as English.
When I was very young in the 70's, I was told to study French because it was the international language.
In the 80's, it was Japanese because they were going to take over the world.
In the 90's, I was told to take Spanish in college because the US was going to be a bilingual country.
As an adult in the 2000's, I watch US helicopter parents scramble to put their kids into immersive Mandarin courses, mimicking the Japanese fad of the 80's.
I'm at least proficient in four languages, none of which are the above four, and my life and career has been just dandy.
It’s very hard to see how those local barriers to entry would reverse the global trend (I might even use a stronger word, closer to juggernaut.)
TBH, automated translation is the only potential I see to reduce the massive need for Chinese language skills in the future. Already we (in the US) get (and choose to use!!) parts whose data sheets are only available in Chinese. It seems clear to me where we are going.
>whose data sheets are only available in Chinese..
What in the supply chain fuck up is that? How do you even get quotes? I've been supply chain at Tesla, Amazon Excelsior metals and i've never, ever had someone send me a data sheet only in chinese.
>It’s very hard to see how those local barriers to entry would reverse the global trend.
Close to 20% of all Chinese exports are easily priced out with a 60% tarrif. Again, you don't need to "Reverse a global trend", you only need to reverse the local barriers to distance trade between the two nations.
So yes, learn that mandarin. Might help you land a job as a project manager for the belt and road initiative in Ghana!
I guess the chinese content is disappointing because lack of freedom of speech. but why don't you travel to china ? to have real conversations with real people
How much time do you spend following someone else's dream?
Wealth is inconsequential if you spend 80 hours a week at a FAANG and have no time left for yourself, to plan a different life. The famous golden handcuffs.
That's not quite true though, you can get a pretty well paid job in FAANG adjacent that leaves you with enough free time too.
Living in expensive areas has a lot of cons too, a social life for instance, which you don't really have in a rural area. If that's not important to you, great, seems like you have it all figured it out, live on a small income in the middle of nowhere, but not everybody's dream looks like this
That's just cope. With that savings rate he can save for 10 years and spend the next 40 years doing his own thing. As long as you keep your standard of living the same.
As a current Nix user, what I would really like is a statically typed language to define builds. Recreating Nix without addressing that feels like a missed opportunity.
For me the killer feature is Windows Support, Ericsson is doing a great job bringing nix into Windows, but the process it's understandably slow, If this project is similar enough to nix that I can kind-off translate easily the zb derivations to nix derivations, I'm willing to use it in windows (It's not like nix has windows programs in the nixpkgs either way I have to bring them in my own).
The problem for me is that I see no benefit on using this over nix language (which I kinda like a lot right now)
We're working on rattler-build (https://github.com/prefix-dev/rattler-build/) - which is a build system inspired by Apko / conda-build and uses YAML files to statically define dependencies. It works really well with pixi (our package manager) but also any other conda compatible package managers (mamba, conda).
And it has Windows support, of course. It can also be used to build your own distribution (e.g. here is one for a bunch of Rust utilities: https://github.com/wolfv/rust-forge)
> Ericsson is doing a great job bringing nix into Windows
Is this Ericsson... the corporation? Windows support for nix is something I don't hear much about, but if there is progress being made (even slowly) I'd love to know more.
Bit of a side note, but COSMIC depends on the rustybuzz text shaper which is deprecated: https://github.com/RazrFalcon/rustybuzz/issues/74. There was some work underway to bring it up to sync with the latest harfbuzz and then handing over ownership to the harfbuzz team, but this seems to have fizzled out.
I think the final remark about a hypothetical language, Rust-like but without all the low-level requirements, is important here. There is essentially no widely-adopted programming language out that feels like a modern ML with a good tooling situation. Until that happens, Rust will continue to awkwardly serve the audience of such a language while never truly being what they want it to be.
It could be even better if despite being from Microsoft wasn't handled like a 3rd party guest language on .NET design decisions, and VS roadmap tooling.
Lots of negativity in here. I for one am excited about the prospect of an editor that is as responsive as I remember Sublime being back in the day, with the feature set I've come to expect from VS Code. An editor like this simply does not exist today, and betting on the Rust ecosystem is entirely the right choice for building something like this in 2023.
Here here. I backed Onivim hoping it was going to shine a light in the darkness, and it seemed promising, but ultimately was abandoned? I think, unsure.
You'd think there would be an arbitrage opportunity in paying more $$$ for London talent. Still surprises me that this hasn't happened after all these years of huge differences.
Top earning UK dev jobs are usually 200k upwards, already. Those numbers don't account for finance and similar industries, which they hire directly and don't use Hired services.
How common is this? Even breaking £150k seems really challenging - FAANGs aren't hiring in London right now, finance seems to require previous finance experience and/or prestigious education even for experienced candidates (I don't know if they really require it or just like to put it in their job ads); and even companies that pay less (£90-120k) aren't giving me the time of day.
I'm making more than that in London. I know similarly qualified people in Bristol who make literally a fifth of my salary yet for some reason do not want to move to London.
Initial HR filter is to weed out the DDOS of a million CVs on a job ad... Look for a backdoor. Friends, neighbors, Meetup, colleagues, online forums such as Twitter or Discord.
It's not just FAANGs that are offering TC that high in London. Have a look at levels.fyi if you want to see some numbers. Possibly not as prevalent nowadays unfortunately.
I have no special insight into the London market, but the fact that it hasn't happened after all these years of huge differences probably indicates that the arbitrage opportunity is not as large as it appears.
It seems like a mistake to measure productivity through salary. A baker in India will make a fraction of a baker in the EU, even if they're making as many breads or more per day.
It may simply be that the the same product is worth less when developed in London rather than SF, due to relative availability of VC, market access restrictions, cultural approaches to monetary compensation or any number of other reasons that have nothing to do with the quality of the code.
How does Meilisearch compare to ElasticSearch from an operational point of view? I've experienced ElasticSearch to be quite painful to maintain, requiring lots of manual tweaking to balance shards and careful design of indices.
I've been using Meilisearch in production for quite some time now, and TBH it has been one of the easiest service to maintain (I mean, it's just a single statically linked binary) and with close to zero configuration.
Is it really "just a single statically linked binary"?
I'd love to use Meilisearch as you describe, but their so-called SDKs are just for clients, so you still need the Meilisearch server listening on localhost.
I would love to see something like SQLite based on Meilisearch (i.e. a fully self-contained search library like https://github.com/mchaput/whoosh). Do you know if such a thing exists?
I was referring to the server daemon, not the client libraries.
But ofc, it's a process not an embeddable library, so you can't just link it against your app like you would with SQLite or rocksdb.
Although it looks like it's build around their core library "milli" though (https://github.com/meilisearch/milli/), so probably something doable in the future?
That's the point! We don't ambition to compete with Elastic on everything (logs, analytics, etc). We are doing search for front-end users with a strong focus on relevancy, speed & developer experience.
You can read a bit more on our documentation https://docs.meilisearch.com/learn/what_is_meilisearch/compa...
A quick question, are there any limits around number of separate indexes we can have with meilisearch? I'm thinking atleast say 20-30K separate indexes to start with.
My use case is that i want to start creating some indexes that are "per-user" and some "per-company" where a company(customer) might have many users. This is to do some sort of double tenant isolation. I will create different keys that have permission to specific indexes and deliver those to the user somehow. My current solution does hacky things with Elasticsearch like adding query filters by user/company-id attributes in the background automatically. But since meilisearch would be customer facing, i need stronger guarantees around permissions per index.
I tried this out a year ago on Meilsearch locally, but haven't stress tested it by creating thousands of them like production.
Or is there a better way to do this. This is also a reason where memory-only systems like Typesense didn't make sense to me. I'm fine with taking a performance hit by going to disk to pull the right index. Not every index will be used all the time. I might also look at sharding/partitioning features if present.
> A quick question, are there any limits around number of separate indexes we can have with meilisearch?
Yes! In v1.0, about 180 indexes under Linux in the same instance[1]. The good news is that I'm personally working on lifting this limitation for v1.1 (planned to release in the beginning of April), which should be able to accommodate an unlimited number of indexes[2] (disk space permits, of course).
Note that having many indexes does have an impact on performance and will keep doing so even after v1.1.
> Or is there a better way to do this.
If it works for your use case, you can try using a single index (or a few indexes) with tenant tokens[3] for multitenancy.
At the time I had seemingly limitless motivation for grinding away on flashcards and other learning materials. My progress was strong and I passed the HSK6 after a year and a half or so of studying, which at the time was the highest level of certification offered. I think they changed the system since and added more levels beyond 6. You can do amazing things if you're dedicated!
Today my Chinese is absolutely unusable, and my views on China have soured to the extent that I don't really want to revive my old skills. My takeaway is that learning one of these languages, the CJK languages, Arabic, or similarly weird languages, is just too much effort and I don't think it's worth it. I clearly had a lot of excess energy at the time that I could've directed towards something better. Knowing Chinese is about as useful as juggling and you might as well get really good at juggling if you're bored. It'll save you a few thousand hours.