In English it is pretty good. But talk to it in Polish, and suddenly it thinks you speak Russian? Ukranian? Belarus? I would understand if an American company launched this, but for a company being so proud about their European roots, I think it should have better support for major European languages.
I tried English + Polish:
> All right, I'm not really sure if transcribing this makes a lot of sense. Maybe not. A цьому nie mówisz po polsku. A цьому nie mówisz po polsku, nie po ukrańsku.
They don't claim to support Polish, but they do support Russian.
> The model is natively multilingual, achieving strong transcription performance in 13 languages, including English, Chinese, Hindi, Spanish, Arabic, French, Portuguese, Russian, German, Japanese, Korean, Italian, and Dutch. With a 4B parameter footprint, it runs efficiently on edge devices, ensuring privacy and security for sensitive deployments.
I wonder how much having languages with the same roots (e.g. the romance languages in the list above or multiple Slavic languages) affects the parameter count and the training set. Do you need more training data to differentiate between multiple similar languages? How would swapping, for example, Hindi (fairly distinct from the other 12 supported languages) for Ukrainian and Polish (both share some roots with Russian) affect the parameter count?
Swahili is subcontinental lingua franca spoken by 200M people and growing quickly. Polish is spoken by a shrinking population in one country where English is understood anyways.
As a Dutch person, I'm very doubtful that's the case, but I'm willing to bet a good ESL speaker is more aware of common grammatical errors than some native speakers. For example, the your/you're mixup makes no sense if you've had to explicitly learn about English contractions in the first place.
Heh, based on my incorrect and probably wrong experience Dutch and Swedes are the best non-native english speakers in term of both the accent and fluency.
Those and Icelandic people. But there's a fun correlation - see how much the US media content is played compared to local one per country. And which countries use subs rather than dubs or voiceovers in cinemas and TV. https://publications.europa.eu/resource/cellar/e4d5cbf4-a839...
If you have exposure to English media from young age and don't get a translation, you learn pretty quickly.
> The model is natively multilingual, achieving strong transcription performance in 13 languages, including English, Chinese, Hindi, Spanish, Arabic, French, Portuguese, Russian, German, Japanese, Korean, Italian, and Dutch.
Yeah, it's too bad. Apparently it only performs well in certain languages: "The model is natively multilingual, achieving strong transcription performance in 13 languages, including English, Chinese, Hindi, Spanish, Arabic, French, Portuguese, Russian, German, Japanese, Korean, Italian, and Dutch"
That's a mix of Polish and Ukrainian in the transcript. Now, if I try speaking Ukrainian, I'm getting transcript in Russian every time. That's upsetting.
Oh no! The model won't translate to an unsupported language, and incorrectly reverts to one that it was explicitly trained on.
The base likely was pretrained on days that included Polish and Ukrainian. You shouldn't be surprised to learn it doesn't perform great on languages it wasn't trained on, or perhaps had the highest share of training data.
Cracking non-English or accented / mispronounced English is the white whale of text-to-speech I think; I don't know about you, but in our day to day chats there's a lot of jargon, randomly inserted English words, etc. And when they speak in English it's often what I call expat-English which is what you get when non-native speakers only speak the language with other non-native speakers.
Add poor microphone quality (using a laptop to broadcast a presentation to a room audience isn't very good) and you get a perfect storm of untranscribeable presentations or meetings.
All I want from e.g. Teams is a good transcript and, more importantly, a clever summary. Because when you think about it, imagine all the words spoken in a meeting and write them down - that's pages and pages of content that nobody would want to read in full.
I'm not sure why but their multilingual performance in general has usually been below average. For a French company, their models are not even close to being best in French, even outdone by the likes of Qwen. I don't think they're focusing on anything but English, the rest is just marketing.
polish logically should be rendered in cyrillic as the cyrillic orthography more closely matches the sounds and consonant structure of slavic languages like polish and russian, although this has never been done for church reasons . maybe this is confusing ai
I think Moltbook is one of the last warnings we get before it is too late. And I mean it.
As someone who spends hours every day coding with AI, I am guilty of running it in "YOLO" mode without sandboxing more often than I would like to admit. But after reading Karpathy's post and some of the AI conversations on Moltbook, I decided to fast-forward the development of one of the tools I have been tinkering with for the last few weeks.
The idea is simple - create portable, reproducible coding environments on remote "agent boxes". The initial focus was portability and accessing the boxes from anywhere, even from the smartphone via a native app when I am AFK.
Then the idea came to mind to build hardened VMs with security built-in - but the "coding experience" should look & feel local. So far I've been having pretty good results, being able to create workspaces on remote machines automatically with Codex and Claude pre-installed and ready-to-use in a few seconds.
Right now I am focusing my efforts on getting the security right. First thing I want to try is putting a protective layer around the boxes, in such a way that the human user CAN for example install external libraries, run scripts, etc, but the AI agent CAN'T. Reliably so. I am more engineer than security researcher, but I am doing pretty good progress.
Happy to chat with likeminded folks who want to stop this molt madness.
Most importantly, Europe needs more trading partners after having lost Russia and now losing the United States. Second, I am happy about German (I suspect it's similar in other EU countries) farmers largely supporting the far-right getting a taste of a world without protectionism and regulations. Finally, I hope for lower grocery prices, not only for myself, but also because it makes the whole social situation less explosive.
Fair trade yes. Unfair trade no. And Mercosur is COMPLETELY unfair to European farmers. It imposes higher standards - and thus costs - on European farmers, while allowing South American farmers to produce with lower quality and adding forbidden substances to grow crops faster - and cheaper.
This is a common meme but wrong.
The imported goods are subject to the same restrictions as those produced within EU.
What hurts EU farmers the most is the big supermarket cartel that controls prices and pushes farmers to produce more and more cheaply (and consumers that react extremely sensitive to every price increase, but that’s a more inconvenient truth)
Definition of a cartel is a combination of independent commercial or industrial enterprises designed to limit competition or fix prices - it can be a cartel that basically oppresses farmers and have low consumer prices as result
On average, South American farmers use 2-3 times more pesticides than farmers in Europe. 2-3 times more would be illegal in Europe, but is allowed as part of Mercosur trade.
Pesticides banned in Europe, but allowed in South America: Atrazine, Acephate, Mancozeb, Paraquat, and many more.
Diseases they can produce include: Parkinson's, brain damage in children and lower IQ, infertility, genetic mutations.
Nothing in the deal says that EU has to accept anything that does not adhere to EU standards. Any food imports have to follow EU regulations. It only allows (a fairly dismal quota) to go through without tariffs.
So all the bullshit you just said (which I am not even sure I trust) is irrelevant.
This can more some of the incredibly polluting meat (beef) industry to countries where the pollution is lower due to less intensive methods over a larger area, which is a win-win.
This is a boon to any European manufacturer and machining company.
This is a bad deal for many European countries that still have a strong farming industry, and for Europeans in general too.
Once again, Germany has pushed through its interests at the expense of other European nations like Poland. This time even France was against it.
What is Germany going to get? A new market for their decaying automobile industry.
What is the rest of Europe going to get? Cheap, low quality food shipped thousands of kilometers. Food produced with lower standards than food produced in the EU - so farmers in Europe now have to face unfair competition.
This is a boon for any European manufacturing and tech company. Not "just" German car manufacturers but especially machining and pharmaceutical companies.
Farming is already incredibly subsidized in the EU, and has an outsized political capital for their importance based on historical momentum. This is also primarily bad for the beef industry, which is produced in the EU using very intensive and polluting (ammonia) methods which are also bad for animal welfare. They deserve no sympathy.
> Farming is already incredibly subsidized in the EU
As it should be if we don't want to wake up one fine day in the middle of a global war with no food supply because of a naval blockade and have our children starve to death.
Mercusor nations only get lower tariffs up to a certain amount. For meat that's roughly 1.5% of EU production. That is no threat to Europe's strategic capacity.
That would happen anyway as the EU is a net importer of fertilizer.
Fortunately there's around 800kg per capita worth of food storage in the EU, so should a war break out we're not all immediately dead - just vegetarian after a period of slaughtering all the livestock that can't be fed.
We can always eat bugs that the EU authorized for human consumption. I would at least. Cricket farms are more sustainable than cattle or pig farming. I like to think of them as grass shrimp.
This kind of incentive should not block trade. If we need sufficient production capacity for security reasons, it’s ok to subsidize it, but the product should still compete on the market and surplus can always be donated to UN. There’s enough starving people on this planet.
Right now the current system is totally inefficient, with a lot of food waste, and a lot of ruined landscapes and soil because of pollution and intrants
We need on the contrary to produce less globally, but more organically, and to reduce waste and produce locally
On the contrary, it's quite apparent today that globalization and free borders have largely failed the people, and that some amount of protectionism should be put back in place
No, it is not apparent. Globalization has driven economic growth in a lot of countries, both developing and developed. There’s steady increase in HDI everywhere, decrease in extreme poverty, less hunger, better education etc etc. Nothing of that would be possible in postcolonial protectionist world. What you are talking about as reasonable amount isn’t protectionist, it’s just a sane set of domestic policies (welfare, education, industrial policy etc) that help countries to survive and grow in globalized world. There’s a difference between gatekeeping local markets and steering local industries for better competition and consumer protection. The latter just sets strict rules, but still allows global players to participate. Automotive sector has plenty of examples like that.
We're speaking of the effect ON DEVELOPED COUNTRIES WORKFORCE, it mostly has failed the people, with jobs sent overseas, and lower quality goods, full of pesticides, coming in. All that for what? Just overconsumption that mostly ends in the trash. A new world IS possible
If you want to use national security as a justification for subsidies, you need to be careful with what you are subsidizing. Only essential things should be subsidized. Non-essential things can be left to the market, or at least their subsidies require other justifications.
From a national security perspective, it is essential to provide basic nutrition to people when international trade is disrupted. Having access to food people enjoy eating is not essential. The viability of existing agricultural businesses is not essential. The preservation of cultural traditions related to food and agriculture is not essential. And so on.
It's also important to consider where the subsidies should be directed. Here in Finland, the explicit justification for agricultural subsidies has always been the assumption that food produced in "European countries that still have a strong farming industry" might not be available during a crisis.
Most of Europe has long reached a population density that makes it effectively impossible to achieve self-sufficiency, so this argument is pointless.
This is going to be a good agreement if it is policed well enough that Mercosur countries are effectively forced to raise their food-production standards (because accepting imports doesn't automatically mean they can ignore regulations on suitability). Europe gets cheaper basic staples and sells LATAM more services and value-added products.
I'd rather help our Latin "cousins" get out of poverty, than having to deal with the insanity of US culture wars.
Shipping food across the globe works great along with green deal. Such food quality is also questionable in many ways because transportability must be #1 priority.
As another commenter pointed out, beef is especially interesting. On one hand EU cries about greenhouse gas and how we should eat less meat. On the other hand goes to reduce price and increase production of beef which such moves. Pure hypocrisy.
I wonder if someone will double down on checking how Brazil is protecting its rains forests? Or will it just look the other way while Europeans eat cheap food that was grown in what was rain forest very recently?
If anything, deepening economic relationships will strengthen European influence over complex issues.
As for transport - enough of this stuff is already transported across the ocean (from LATAM but also South Africa, for example) that I doubt there will be much of a change.
The eu is a net exporter of agricultural products, what you are saying is plainly false.
The problem is rather the inputs, mainly from mineral sources, used for the production and imported from countries such as Morocco or Russia (before the war). Mercosur doesn't solve any of those problems, and will decrease the EU food autonomy as farms will disappear due to the LATAM dumping.
Meat is incredibly bad for food security. If this scenario happens we will have to stop nearly all meat production and become forcibly vegetarian, like some countries did in WW2.
You only need to control 2-3 chokepoints to hugely impact shipment - especially of perishables. The Panama Canal + Caribean + Gibraltar and you get no food in Europe.
Most beef in the EU is a byproduct of the dairy industry. Beef meat comes from culled dairy cows, and a lot of production is done on land that isn't suitable for other uses (mountains, for instance). The EU has also the highest norms in the world regarding food production, and they are tightly enforced, unlike LATAM where a lot of cattle is grazed on deforested land with no regulation regarding chemicals.
What you are saying is very misleading if not plain false.
Restricting the analysis purely to economics is a big mistake, imho, like it was during the Brexit referendum in the UK.
Even in France agriculture is a very small percentage of the GDP and jobs. But what has happened is a demonstration of the loss of sovereignty with the EU effectively imposing something against the wish of the country. So the significance is political, and we'll see if that has tangible political effects or not.
Amazing, we sell them our gadgets and in return we get growth hormone beef and other agricultural products which don't even meet 1980s EU regulations, big win indeed
God forbid we subsidize food too, it's only like the #1 priority when it comes to sovereignty after all, we should definitely not produce locally and rely on foreign countries for our food autonomy
How come folks seem to focus on beef, while IMO the real stakes are in obtaining access to important minerals. Lithium, nickel, copper, graphite, niobium, etc. are often listed. There's a nice breakdown on EC pages:
You are just fearmongering based on lies. "Hormone raised cattle", and shit like that.
South America likely has the best beef in the world (I can speak from experience having lived on both sides of the pond). Good that I might have access to real meat here for once.
> 100% definitely use antibiotics and hormones banned in europe for safety reasons
No it's not. South American meat, particularly from Argentina, Uruguay, and Southern Brazil is phenomenal. It's just the perfect geography and climate for cattle.
You are just crying for protectionism. If a less than 2% quota over the European production threatens you, it speaks more about your inability to do your job properly.
Yes of course, and the energy or minerals lobbies don't have any kind of agendas of course. They're obviously working for your well being and not serving their interests
Also, one of the most corrupt country in the world will obviously play by the rules
As far as I know, there is a limitation to how much food is shipped and tied to a percentage of EU farming. So no, the european market will not be flooded.
This exact thing is was said about Poland when they joined the EU, the truth was that French/Spanish/German farmers didn't want to give up non specialized farming, and the same argument has been made and was a primary reason why Ukraine is not in the EU.
Plus it's odd that specifically this deal is so bad, but deals with importing Asian grown food via trade deal is fine.
Wait and see how it goes. This deal might have real political consequences countries opposed to it, especially in France because of the opposition to the deal and by demonstrating that the country no longer has control: so this is a vindication for eurosceptic parties and embarrassing for the most pro-EU ones. This may just be short-term anger, and the whole establishment will push for it to be forgotten asap as the Presidential elections are in just a bit more than a year away.
From a pragmatic perspective it’s just common sense. Europe cannot produce food at prices its population expects. It has no cattle herd to speak of yet consumes lots of beef. It wants for multiple commodities which don’t grow there. And as time goes on there’ll be less and less food production in Europe.
And the idea that food products from SA are low quality is a very old and uninformed take. For better or worse SA has invested heavily in technology in the agricultural sector. Researches from Europe go to Brazil to learn about cattle genetic improvement and farming, not the other way around.
Most of the EU economy comes from services and manufacturing. They’re ensuring a market for that larger base. Angering the small percentage of farmers to ensure food supply and manufacturing survival is the trade off.
The prices partially were affected by green deal stuff and other home-grown regulations. Maybe regulations should be lowered instead of letting in cheaper produce from locations where such regulations don’t apply?
Funny, I think this deal was better for the EU than for Mercosur. Still a net positive for both sides though.
That European farmers are crying over wanting more protectionism is nothing new.
The quotas for food imports to EU are dismal, and the food needs to adhere to EU standards anyway. But even that is being cried about as "unfair competition".
I hope you won't get a reality check if one day there is a famine in Europe caused by outsourcing the entire farming to other continents. The very first thing any enemy force would do is a naval blockade, the rest is patience and lots of deaths.
Farming already is heavily subsidized in every EU country. The whole sector only exists as is precisely because of the fears you point out. And that is perfectly fine, because statistically speaking it already is a rounding error both in share of employment and share of GDP (1.2% of EU GDP), only kept alive for the exact purpose you talk about.
So even if these lobby talking points would be true, and everything had to be 100% subsidized, that wouldn't be a problem.
Is it fair to put an entire continent in a position where it does not belong? If I recall correctly Australia and New Zealand were mostly colonized by the British Empire, not by "Europe", Canada by UK and France, US by Western Europe, etc. Europe is a continent, not a country, and Europe did not colonize anything, some countries did.
Europe did not colonize the world - some European countries did. I come from Poland, a country that never colonized another country, so I do not need that moral lecturing.
It is not even a matter of fairness, but of defending one owns interests.
Fellow bootstrapper here, roughly in your ballpark - €4M+ revenue, team of 18, bootstrapped for 12 years.
Only bootstrappers understand the bootstrap hustle ;) But what an amazing business you have built there - be proud, you deserve it.
Let me share a personal founder story if I may: after 12 years of building the company, I decided to step down as CEO, moved on and spent the last 6 months working on different projects, learned A LOT about AI coding, went to Iceland, Texas. Had a great time. Yet after only 6 months I experienced the strongest "pull" you can imagine, back to my bootstrapped company of 12 years. And here I am - December has been an amazing time, getting back to work. And next year we have ambitious plans ahead!
They leave for Germany, of all places. Germany is one of the European states with most arrests for posting entries on social media. I guess they will pack their stuff and move on in 1-2 years from now.
Germany has a big alt-rising in the form of AFD, and consequently, they do track social media heavily. There is also a non-insignificant fundamentalist Muslim population.
For things like troll posts or just general hate speech, most of the time the police visit your house and ask you questions and give you a stern warning. And remember, police in EU isn't like police in US - when you get visited by police in EU, you aren't afraid that you are going to get shot up or thrown on the ground and tazed if you did nothing wrong.
In extreme cases where you are calling for things like beheading, yea they def arrest for that.
Source: close friend that lives in Germanty works for a company that does business with German government. I don't know first hand but he is pretty aware of the policics in EU and I have no reason to believe he would be exaggerating.
On anther note, Germany policing is quite progressive actually. For example, if you run, you don't get a charge for evading/eluding - its actually legal to run from police because "desire for freedom is a human right".
In France, discriminatory identity checks are a striking illustration of this. Police disproportionately target certain citizens on the basis of their skin color or presumed origin, particularly young people perceived to be Black or Arab, including children. These abusive controls can often lead to more serious police violence, including with fatal outcomes.
> "big alt-rising in the form of AFD, and consequently, they do track social media heavily. There is also a non-insignificant fundamentalist Muslim population"
They are not though alt-right movements all work on shifting the blame. They always find a scapegoat (jewish people in WW2) for material conditions instead of attacking the root causes.
It seems reasonable to be concerned about a government that wants the power to reveal Internet users, but I couldn’t say on what basis Proton expects legal protection to continue after the move.
Neither of your links mention arrests, one specifically says "None of the suspects were detained". They don't seem to back up the original claim about Germany arresting the most people based on social media posts.
That’s an important distinction. Thank you for referring back to the original wording. They were investigated for violating the criminal code, searched, interrogated, and had devices seized in a number of cases, but seemingly not arrested.
as a german i can confirm that this happens very frequently (way more often than you think). usually it's politicians who file police reports which get prosecuted most of the time. i believe the last government (left wing coalition) built up massive infrastructure to prosecute such offenses. politicians in germany get special protection in terms of speech laws. §188 StGB allows the state to prosecute you severely, even without a private complaint from the politician in some cases.
I just tried "analyze this audio file recording of a meeting and notes along with a transcript labeling all the speakers" (using the language from the parent's comment) and indeed Gemini 3 was significantly better than 2.5 Pro.
3 created a great "Executive Summary", identified the speakers' names, and then gave me a second by second transcript:
[00:00] Greg: Hello.
[00:01] X: You great?
[00:02] Greg: Hi.
[00:03] X: I'm X.
[00:04] Y: I'm Y.
...
I made a simple webpage to grab text from YouTube videos:
https://summynews.com
Great for this kind of testing?
(want to expand to other sources in the long run)
I saw the keyboard to be operated by the left hand only and here is my (totally personal and somewhoat adjacent) problem with it.
My left hand is the one which has suffered the most the many hours of using a keyboard over the last +-25 years. While the right hand has the occasional break from the keyboard when using the mouse, the left hand is constantly glued to the keyboard.
It also has a much tougher job - all the cmd, ctrl, alt and shift + combinations are mostly done using the left hand - e.g. on Mac you cannot cmd+shift+ select text with the arrows - you must use the left hand - so it ends up doing so much more work.
I wonder if there are other people with the same problem. My right hand never hurts after many hours of computer work - but the left hand does. It hurts even now that I am typing and I haven't even spent more than an hour doing it.
Please do your hands a favor and get yourself an ergonomic keyboard! Thumb keys especially alleviate the issues with modifiers that you're describing.
I use a Glove80 as my daily driver right now, although the price tag to build quality ratio is not amazing, so idk if I would recommend it particularly. But there's a massive world of ergo keyboards out there--surely the right one for you exists somewhere!
I'm at the point where I need to redefine cmd-z, x, c, v because my left thumb doesn't want to do that dance anymore. It's been painful for a year, and I finally got to the point of redefining it a couple weeks ago. And the muscle memory is so ingrained that I changed it to option ', 1, 2, 3 and never thought about the idea that my right hand could do it.
They started with the left hand as requested, but made right hand version as well.
I wish these were also commercially available... I'd love to pay for one of these... I know it's open sources, but I don't know the language nor do I have the skills to construct one myself.
I was getting hand pain, switched to a Totem keyboard. 38 keys, 6 thumb keys. Column splay & never reaching for number row has greatly helped. 20g actuation means little force needed
Rust has been such a "pain" to learn - at least compared to other, more straight-forward languages. But boy does it feel good when you know that after a few back and forths with the compiler, the code compiles and you know, there is not much that is going to go wrong anymore.
Of course, I am exaggerating a bit - and I am not even that experienced with Rust.
But after coding with Ruby, JS/TS and Python - it feels refreshing to know that as long as your code compiles, it probably is 80-90% there.
Rust is the most defect-free language I have ever used.
I'd wager my production Rust code has 100x fewer errors than comparable Javascript, Python, or even Java code.
The way Result<T,E>, Option<T>, match, if let, `?`, and the rest of the error handling and type system operate, it's very difficult to write incorrect code.
The language's design objective was to make it hard to write bugs. I'd say it succeeded with flying colors.
Now try an actual functional programming language. I like Rust too but those features all come from FP, and FP languages have even more features like that that Rust doesn't yet or can't have.
> Rust has been such a "pain" to learn - at least compared to other, more straight-forward languages. But boy does it feel good when you know that after a few back and forths with the compiler, the code compiles and you know, there is not much that is going to go wrong anymore.
I found that at some point, the rust way kinda took over in my head, and I stopped fighting with the compiler and started working with the compiler.
One big source of bugs in TS is structural sharing. Like, imagine you have some complex object that needs to be accessed from multiple places. The obvious, high performance way to share that object is to just pass around references wherever you need them. But this is dangerous. It’s easy to later forget that the object is shared, and mutate it in one place without considering the implications for other parts of your code.
I’ve made this mistake in TS more times than I’d like to admit. It gives rise to some bugs that are very tricky to track down. The obvious ways to avoid this bug are by making everything deeply immutable. Or by cloning instead of sharing. Both of these options aren’t well supported by the language. And they can both be very expensive from a performance pov. I don’t want to pay that cost when it’s not necessary.
Typescript is pretty good. But it’s very normal for a TS program to type check but still contain bugs. In my experience, far fewer bugs slip past the rust compiler.
Appreciate it, that makes a lot of sense. I feel like I've been trained to favor immutability so much in every language that I sometimes forget about these things.
Yes, immutability is great for safety. But the copies you have to make to keep everything immutable extracts a price in copies and garbage collection.
Rust is advertised as having fearless concurrency. That's true, but not that important as concurrency is not that common. What's important to everyday programming is Rust provides fearless mutability. The fearless concurrency you get with that is just a bonus.
Fearless mutability provides Rust the same safety as a functional language in a without the speed or space cost. IMO, it's Rust's true secret sauce.
Similar. I mostly design my code around something like pipe and lifetime. The longer something needs to live the closer it is to the start of the program. If I need to mutate it, I take care that the actual mutation happens in one place, so I can differentiate between read and write access. For anything else, I clone and I update. It may not be efficient and you need to track memory usage, but logic is way far simple.
Not parent comment, but TS is generally safe if you have types correct at system borders, but very scary when you don't. Some of the most impactful bugs I've seen are because a type for an HTTP call did not match the structure of real data.
Also, many built in functions do not have sufficient typesafey like Object.entries() for instance
That is an issue with how TS works, but it can be significantly improved upon by using a library to verify the structure of deserialized data. zod is one example, or you could use protobufs. Fundamentally, this is an issue with any programming language. But having your base "struct"-like type be a hashmap leads to more mistakes as it will accept any keys and any values.
I disagree that this is an issue in every language - the problem is that in other languages the validation against some schema is more or less required for unmarshalling, and it's optional in TS.
Seeing a deserialization error immediately clues you in that your borders are not safe. Contrast that with TypeScript, where this kind of issue can lead to an insidious downstream runtime issue that might seem completely unrelated. This second scenario is very rare in other languages.
I don't know Rust, and I'm genuinely curious: How does it improve over that problem?
When you call a REST API (or SQL query for that matter), how does it ensure that the data coming back matches the types?
TS allows you to do parse the JSON, cast it into your target type, done (hiding correctness bugs, unless using runtime verification of the object shape, see sibling comment). Does Rust enforce this?
It validates the object shape at runtime, much like you can do in Typescript with a library like Zod. The key difference in this case is that Rust makes it scary to not validate data while Typescript will gladly let you YOLO it and blow your legs off, even in strict mode.
It’s not. And trying to just be a transformation of the source to JS without its own standard library (mostly, some old stuff doesn’t follow this) means it really isn’t possible with just TS alone.
That’s OK with me. I use TS because I like it and hate the total lack of safety in JS. I have to use JS on the web, so TS it is.
If I don’t need it to run on a webpage, I wouldn’t be writing it in TS. I like other languages more overall.
If you type correctly at border of your system, then TS will be very close to a formal verification of your code. This won't catch all bugs, but even broad categories for you data is helpful. If you know your input is a non-null string. Then it will warn you of every non string usage. It won't catch whether it's a name or an email, but knowing someone tries to divide it by zero is helpful.
Typescript doesn't even support notions like "unsigned integer". It is not a serious attempt at type-safety; its main claim to fame is "better than raw Javascript" which is not saying much.
I’ve never been a JS on the server person, I was used to other languages when that was developed.
Well I think I would prefer python, but simply because it’s “more traditional“ and I realize that’s specious reasoning, I prefer to use strongly typed languages whenever possible.
I would generally reach for Java since it’s the language I’m most proficient in due to my career. There’s also Go, which I played with long ago, or maybe I’d try Rust.
This is only for anything important. If I was just toying with something locally I’d probably do whatever was fastest. In that case Python or JS might be my choice for a very tiny script.
For the longest time I had been using GPT-5 Pro and Deep Research. Then I tried Gemini's 2.5 Pro Deep Research. And boy oh boy is Gemini superior. The results of Gemini go deep, are thoughtful and make sense. GPT-5's results feel like vomiting a lot of text that looks interesting on the surface, but has no real depth.
I don't know what has happened, is GPT-5's Deep Research badly prompted? Or is Gemini's extensive search across hundreds of sources giving it the edge?
I’ve been using `Gemini 2.5 Pro Deep Research` extensively.
( To be clear, I’m referring to the Deep Research feature at gemini.google.com/deepresearch , which I access through my `Gemini AI Pro` subscription on one.google.com/ai . )
I’m interested in how this compares with the newer `2.5 Pro Deep Think` offering that runs on the Gemini AI Ultra tier.
For quick look‑ups (i.e., non‑deep‑research queries), I’ve found xAI’s Grok‑4‑Fast ( available at x.com/i/grok ) to be exceptionally fast, precise, and reliable.
Because the $250 per‑month price for Gemini’s deep‑research tier is hard to justify right now, I’ve started experimenting with Parallel AI’s `Deep Research` task ( platform.parallel.ai/play/deep-research ) using the `ultra8x` processor ( see docs.parallel.ai/task‑api/guides/choose-a-processor ). So far, the results look promising.
I don't know about Gemini pro super duper whatever, but the freely available Gemini is as sycophantic as ChatGPT, always congratulates you for being able to ask a question.
And worse, on every answer it offers to elaborate on related topics. To maintain engagement i suppose.
The ChatGPT API offers a verbosity toggle, which is likely a magic string they prefix the prompt with, similar to the "juice" parameter that controls reasoning effort.
I tried English + Polish:
> All right, I'm not really sure if transcribing this makes a lot of sense. Maybe not. A цьому nie mówisz po polsku. A цьому nie mówisz po polsku, nie po ukrańsku.
reply