Does JLC now easily allow you to use any component that’s available from LCSC? Last time I checked, there was only a limited component library available for the standard assembly process.
Ah yeah, maybe it's easier than they make it seem, but I've found PCBWay preferable for small batch assembly because they just take a list of MPNs and give you back a quote, which is the service that I really want. Preordering etc. is detail that I don't really want to care about.
This is exactly what I like about JLC - the fact that some human doesn't have to be involved in the quoting process and that I can select parts from LCSC. The software handles everything.
Getting a human involved in quoting makes it more expensive and it gives these vendors an opportunity to BOM substitute for cheaper Chinese alternative parts.
Totally fair that you prefer JLC's approach. There's clearly room in the market for different models.
Part substitution is mainly a question of trust. As far as I understand it, you preorder parts through JLC's website, so JLC could easily automatically sub out your passives if they wanted to. For all that people worry about this a lot, I'm not sure if the incentive to do it is really there for shops like JLC or PCBWay. The components that are easy to substitute are cheap anyway, and these companies can easily just pass on any additional cost to the customer. I'm not personally going to haggle with PCBWay over a few additional pennies for a chip resistor or ceramic capacitor, given that the entire service is mind-blowingly cheap.
It doesn't meet a perfect theoretical definition of net neutrality, but it's a set of defined legal limits on the extent to which providers can treat different kinds of traffic differently.
Net neutrality is not theoretical, it is literally the default setting.
Any deviation from that default requires special effort be taken to identify network traffic and treat it differently, and as soon as you have made that effort you cannot truthfully claim to have net neutrality. The UK does not prohibit net neutrality but it does not require it either (according to the comment I replied to which I have not verified).
I guess to me this seems a bit like saying that free markets are the default setting. We’re not in some kind of perfect state of nature. We’re in a complex interconnected society where virtually everything of any importance is regulated to some extent. What you’re saying seems like saying “as soon as you impose one regulation you no longer have a free market”.
This non sequitur strains my ability to assume good faith on your part. We're not talking about markets, we're talking about a utility.
Does your water company bill you differently depending on what you use the water for? Your gas company? Electric? This is not a complicated concept to understand, please make an effort.
What would be the model of a country with stronger net neutrality laws? I think EU regulations are now a touch stronger than UK regulations due to post-Brexit divergence, but by world standards, the UK has strong net neutrality protections.
This isn’t a serious contribution to the discussion. The overall level of NHS services would clearly be far lower (non-existent in some cases) without the contribution of immigrants.
Do you believe that foreigners should be allowed to practice as nurses with fake qualifications? Because the NHS does. As they were ACTIVELY working while the NHS knew about the forgery.
Do you have evidence that there is a widespread, institutional fake qualifications problem with native NHS nurses? Please provide evidence. This is what would show that foreign workers in the NHS do not drag down standards on average.
We’re not going to figure out a practical way to improve the NHS with this level of debate. We get that you don’t like foreign nurses, but I’m not going to respond to your rhetorical questions.
You put words in my mouth, that's a dishonest way of arguing :)
I never once said all foreign nurses or bad, nor did I say I dislike them. I pointed out widespread, institutional level fraud that puts patients at risk, exclusively by foreign NHS staff.
It's worrying you can't respond to the argument without strawmans. Is patient safety a concern for you or does politics trump it?
You know that the NHS crucially depends on immigrant doctors and nurses and that their contribution is overwhelmingly positive. Your original comment was a completely transparent attempt to derail the discussion with a single cherry picked example.
Foreign NHS workers can be 'overwhelmingly' competent AND still drag down standards on average due to widespread fraud. You seem to be avoiding any questioning of specific groups engaging in institutional fraud.
Is fraud a problem or not? Should we have standards at all? Does patient safety matter or should we let fake nurses put patients at risk KNOWINGLY?
There aren't anywhere near enough British nurses for the NHS to use only British nurses. Can you point to a credible long term plan to change that situation? That's what you'd do if you had a goal beyond just stirring up unjustified mistrust of foreigners.
> The issue is compounded by the fact that successive governments say they want to be tough on immigration, but actually do the opposite.
There’s a simple explanation for this. Being “tough” on immigration would be bad for the economy, bad for the NHS, and bad for the country as a whole. So once a party is actually in government, they don’t want to do it, whatever they said in order to gain votes during the election campaign.
Or, maybe massively restricting immigration is actually a great idea and the establishment is conspiring to prevent it. Just like with Brexit, right?
High immigration is the cheaper short term solution at the "cost" of other, deeper issues. Restricting immigration is only be "bad" for the economy because systemic issues are not tackled.
The NHS relies on foreign workers. Why? Because salaries and conditions are shit so locals either do not train for those jobs or give up and moce to Australia at some point. It is cheaper to keep it that way.
12% of 25-34 years old are "economically inactive", which means deep systemic issues.
Generally immigration also keep salaries lower and also productivity lower (and that's why the left is actually historically not too keen).
This is difficult to debate seriously because there is always someone to cry "racist".
If you actually put the fixes for those “systemic issues” on the table, it’s obvious that no-one is going to vote for them, so they’re total non-starters. E.g. it would be great to pay nurses more, but no-one is going to vote for the tax hike required to fund it.
If any of this is difficult to debate seriously, that’s because opponents of current immigration policy consistently appeal to the lowest common denominator (people’s prejudices) rather than framing a proper argument. Even in this thread, you can see someone trying (absurdly) to redirect the discussion towards some Nigerian nurses with fake qualifications.
There’s a simple explanation for this. Being “tough” on immigration would be bad for the economy, bad for the NHS, and bad for the country as a whole. So once a party is actually in government, they don’t want to do it, whatever they said in order to gain votes during the election campaign.
You missed one important point: A rational party, or at least one with a rational leader. If you're dumb enough you will go through with it no matter how much it hurts your economy, your health system, and your country as a whole. I'm not in the UK but maybe someone from there could provide an estimate, on a scale of 0 to Trump, where does Farage rate?
But on the other hand, claiming that, as mentioned, any alternatives to high immigration is bad for the country has to be BS because it does not pass the "smell test". I never understood this stance that countries must have high immigration, that high immigration is good (TM) and that anything else is bigoted and racist. Best theory is that anti-racism has mutated into a monster mixed with business interests only interested in an ever growing labour and consumers pool.
You're conflating terrorism with irregular warfare. The Oradour-sur-Glane massacre was terrorism committed by regular forces; the French resistance blowing up a German supply train was non-terrorist action by irregular forces.
The presupposition behind that question is that immigration is a necessary evil to be limited as much as possible. I am not American, but that strikes me as an ironic position for Americans to take.
In my experience these models work fine using another language, if it’s a widely spoken one. For example, sometimes I prompt in Spanish, just to practice. It doesn’t seem to
affect the quality of code generation.
Thank you. +1.
There are obviously differences and things getting lost or slightly misaligned in the latent space, and these do cause degradation in reasoning quality, but the decline is very small in high resource languages.
It just can’t be a case simply because how ML works. In short, the more diverse and high quality texts with reasoning reach examples were in the training set, the better model performs on a given language.
So unless Spanish subset had much more quality-dense examples, to make up for volume, there is no way the quality of reasoning in Spanish is on par with English.
I apologise for the rambling explanation, I sure someone with ML expertise here can it explain it better.
I saw a curious post recently that explored this idea, and showed that it isn’t really the case. The internal layers of the model aren’t really reasoning in English, or in any human language.
Translation in/out of human languages only happens at the edges of the model.
Internal layer activations for the same concept are similar regardless of language, while activations at the top/bottom layers diverge. Meanwhile the pattern is reversed for same language different content.
So we do at least agree on the fact that quality of human language <-> embeddings transition depends on how good target language is represented in the training dataset?
Even if it happens at the edge, on every conversation turn, I may assume non captured small subtleties of meaning over time can accumulate into significant error.
The agent may be translating to English behind the scenes. There are all kinds of hacks layered on top of the underlying models. But however exactly it works, it’s clearly not the case that these things only make use of Spanish training data when you prompt them in Spanish.
Lets take a language with orders of magnitude less training data, like Nahuatl. The following is what happens if I ask Claude Code in Nahuatl to give me an example of a simple program that I can execute inside a web browser (avoiding any direct keyword prompts like 'Javascript' or 'Hello World'). Interestingly, it responds in Spanish. I doubt that it has any relevant training data in Nahuatl. (Apologies if the Nahuatl is wrong – I just used Google translate.)
¿Uelis techmakas se neskayotl tlen se programa tlen amo ouij tlen ueliskia nijchiuas ipan se navegador web?
-----
Entiendo tu pregunta en náhuatl. Aquí un ejemplo sencillo — una calculadora en HTML puro que puedes abrir directo en el navegador, sin servidor:
<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8">
<title>Calculadora</title>
<style>
body { font-family: sans-serif; display: flex; justify-content: center; padding: 40px; }
.calc { border: 1px solid #ccc; padding: 20px; border-radius: 8px; width: 200px; }
input { width: 100%; margin-bottom: 10px; font-size: 1.2em; text-align: right; }
button { width: 22%; margin: 2px; padding: 8px; font-size: 1em; cursor: pointer; }
.wide { width: 47%; }
</style>
</head>
<body>
<div class="calc">
<input type="text" id="pantalla" readonly>
<div>
<button onclick="tecla('7')">7</button>
<button onclick="tecla('8')">8</button>
<button onclick="tecla('9')">9</button>
<button onclick="tecla('/')">÷</button>
<button onclick="tecla('4')">4</button>
<button onclick="tecla('5')">5</button>
<button onclick="tecla('6')">6</button>
<button onclick="tecla('*')">×</button>
<button onclick="tecla('1')">1</button>
<button onclick="tecla('2')">2</button>
<button onclick="tecla('3')">3</button>
<button onclick="tecla('-')">−</button>
<button onclick="tecla('0')">0</button>
<button onclick="tecla('.')">.</button>
<button onclick="tecla('+')">+</button>
<button onclick="limpiar()">C</button>
<button class="wide" onclick="calcular()">=</button>
<button class="wide" onclick="borrar()">⌫</button>
</div>
</div>
<script>
const pantalla = document.getElementById('pantalla');
function tecla(val) {
pantalla.value += val;
}
function calcular() {
try {
pantalla.value = eval(pantalla.value);
} catch {
pantalla.value = 'Error';
}
}
function limpiar() { pantalla.value = ''; }
function borrar() { pantalla.value = pantalla.value.slice(0, -1); }
</script>
</body>
</html>
Guarda esto como calculadora.html y ábrelo en cualquier navegador — no necesita servidor ni dependencias. Es un buen punto de partida para aprender HTML,
CSS y JavaScript.
> it’s clearly not the case that these things only make use of Spanish training data when you prompt them in Spanish.
It’s not! And I’ve never said that.
Anyways, I’m not even sure what we are arguing about, as it’s 100% fact that SOTA models perform better in English, the only interesting question here how much better, is it negligible or actually makes a difference in real world use-cases.
It’s negligible as far as I can tell. If the LLM can “speak” the language well then you can prompt it in that language and get more or less the same results as in English.
Mac has about 15% of the market share in the US. It's not really a niche.
$3500 is more than I would spend on a hobby too, but there are, in absolute terms, a large number of Americans who can spend this much on their hobbies.
reply