A counter example to this is that I asked it about NovaMin® 5 minutes ago and it essentially told me to not bother and buy whatever toothpaste has >1450 ppm fluoride.
Such is the nature of probabilistic systems. Generally speaking, LLMs read the top N search results on the topic in question and uncritically summarize them in their answer. Emphasis on uncritically, therefore the quality of LLM answers is strongly correlated with the quality of top search results.
This is why I am so excited about the way GPT-5 uses its search tool.
GPT-4o and most other AI-assisted search systems in the past worked how you describe: they took the top 10 search results and answered uncritically based on those. If the results were junk the answer was too.
GPT-5 Thinking doesn't do that. Take a look at the thinking trace examples I linked to - in many of them it runs a few searches, evaluates the results, finds that they're not credible enough to generate an answer and so continues browsing and searching.
That's why many of the answers take 1-2 minutes to return!
I frequently see it dismiss information from social media and prefer to go to a source with a good reputation for fact-checking (like a credible newspaper) instead.
> finds that they're not credible enough to generate an answer
The credibility is one side of the story. In many cases, at least for my curious research, I happen to search for something very niche, so to find at least anything related, an LLM needs to find semantic equivalence between the topic in the query and what the found pages are discussing or explaining.
One recent example: in a flat-style web discussion, it may be interesting to somehow visually mark a reply if the comment is from a user who was already in the discussion (at least GP or GGP). I wanted to find some thoughts or talk about this. I had almost no luck with Perplexity, which probably brute-forced dozens of result pages for semantic equivalence comparison, and I also "was not feeling/getting lucky" with Google using keywords, the AROUND operator, and so on. I'm sure there are a couple of blogs and web-technology forums where this was really discussed, but I'm not sure the current indexing technology is semantically aware at scale.
It's interesting that sometimes Google is still better, for example, when a topic I’m researching has a couple of specific terms one should be aware of to discuss it seriously. Making them mandatory (with quotes) may produce a small result set to scan with my own eyes.
A year ago I asked it to do deep research on Biomin F + a comparison to NovaMin & fluoride. It gave a comprehensive answer detailing the benefits of BioMin & NovaMin over regular fluroide.
What's incredible about that is that you are acting like that was a success story but it is a nuanced topic and it swallowed all the nuance and convinced you.
You're now here telling us how it gave you the right answer, which seems to mostly be due to it confirming your bias.
I've just spent past week building a medium complex web app for editing configs at $work, so I can chime on this.
Having worked with earlier versions of sveltekit in the past, I have to say the new reactivity system is not that bad and pretty easy to wrap your head around. Once you're used to the runes (there's like 4 you have to remember) you can just focus on building stuff and it's really quite a pleasant and productive dev experience. I've gotten multiple compliments from people about the speed and quality I was able to deliver this with and that's in large part due to sveltekit.
I do have to give a shout out to good ol' bootstrap for allowing me to build something that looks good, works on mobile and is just easy.
While the factors you mention may (or may not) cause Germany to dip into a recession in the near future, calling it a "collapse of the economy" is of course gross hyperbole. Boom and bust cycles are an expected and well studied feature of developed economies.
Let's say you're initializing a huge array on boot that takes 100ms. Packaging everything into a single .js file won't change that. Taking a snapshot of the state after boot and using that for subsequent boots will allow you to skip that.
Sure you can, just click the "x" on the top right of the shorts row and they will be gone. Though, you might have to re-hide them every x days, but still if you don't want to watch them you really don't have to.
This is just AI generated blogspam. The real meat appears to be on [0], but it's behind a paywall which none of the archivers appear to have circumvented. Really unfortunate, because the content looked highly interesting!
My company has built quite a few complex capacitor + Angular + Ionic apps and the performance on iOS is fine. Some even got featured by Apple, so that should be some indication that quality and performance was alright.
I'm assuming they are referring to "traditional old Asian culture" aka the combination of old patriarchal/sexist beliefs, a toxic workplace/exploitation culture, society-over-individual attitudes, and that topped up with a healthy dose of racism to xenophobia (depending on the country).
I mean, some of this is rich to talk about given I'm European and most Western countries share a lot of these traits, but from what I hear(d) from friends from Asia, it's the "the needs of the society/family are more important than those of the individual" that they find the worst compared to the very individualist attitudes of Western countries.
Oh, absolutely, and it can be seen for example in suicide rates [1], or the weird state of Japanese criminal justice where prosecutors will only go for nailed-shut cases so that they don't "lose face" (while society as a whole suffers) [2], not to mention the entire issue surrounding "forced confessions".
By definition, negative side effects that can be cherry-picked are more numerous and pronunced in an Individualist society, as the very point of Collectivism is to steer the crowds away from trouble, while Individualism tolerates a wider range of individual tragedies for the potential upside.
Your examples were not well chosen anyway, as their relation to collectivism seems dubious, and US prosecutors also have high conviction rates without trial through threat of big punishment.
yes of course, the enlightened Americans are so much better at handling crime. pointing at western justice systems to say that western values are superior - this must be satire?
This seems like an uncharitable reading. I don't think there was a comparison made.
Any justice system with a very high conviction rate is either unjust or extremely selective. The American federal government is also extremely selective in prosecution, and for the same reason. Losing makes the prosecutor look bad.
East Asian wars tend to be drastically more deadly than the wars of any other group. The Three Kingdoms War wiped China's population to 30% of what it once was, and had half the deaths of WWII in a world with two hundred million people instead of billions.
"Society" in this context can also mean "a tiny number of primarily self-interested individuals". That tends to be evident when the most powerful or influential people also happen to be strict authoritarians.
Individualism in western countries varies quite a bit. In cross-country scores, Spain has numbers far closer to the middle east than to the US, and then Peru is closer to China than to Spain!
So your invdidualism argument is only strong if by western, you mean the anglosphere, the Netherlands and Belgium.
Even within China, the north (wheat-growing culture) is noticeably more individualistic than the south (rice-growing culture). The south is also significantly more traditional.
Japan and Korea, despite being in North-East Asia, are rice-growing, due to their oceanic climate. Culturally they are also closer to Southern China.
A shallow and superficial comment in a subthread that took the wrong turn. Casually applying nasty labels in an act of self-loathing from a fellow German. Oh no, our toxic workplaces, truly funny. Our beloved individualism that has little regard for society as a whole left, consequences of that showing up more and more, how dare the old asian guy hold on to the old ways. "Xenophobia" in the face of mass immigration that is handled terribly etc.
Actually take your criteria and apply them fairly to some of the other cultures around the world. And let the old guy smoke (outside). He is not the worst human ever, that's for sure.
We use Semgrep Supply Chain at work and are reasonably satisfied with it. It splits the supply chain vulnerabilities it found into the categories: reachable, unreachable and undetermined. This makes triaging much easier and it has reduced the time we spent on assessing new vulnerabilities by quite a lot.
