guys why does armenian completely break Claude(twitter.com) |
guys why does armenian completely break Claude(twitter.com) |
Then they changed the architecture so voice mode bypasses custom instructions entirely, which was really unfortunate. I had to unsubscribe, because walking and talking was the killer feature and now it's like you're speaking to a Gen Z influencer or something.
but also, getting shut down for safety reasons seems entirely foreseeable when the initial request is "how do I make a bomb?"
Copy-pasted from the chat: https://www.google.com/search?q=translate+%D5%AB%D5%B6%D5%B9...
I believe fans have provided a retroactive explanation that all our computer tech was based on reverse engineering the crashed alien ship, and thus the arch, and abis etc were compatible.
It's a movie, so whatever, but considering how easily a single project / vendor / chip / anything breaks compatibility, it's a laughable explanation.
Edit: phrasing
Still dumb but not as dumb as what we got.
Given that the language of the thought process can be different from the language of conversation, it’s interesting to consider, along the lines of Sapir–Whorf, whether having LLMs think in a different language than English could yield considerably different results, irrespective of conversation language.
(Of course, there is the problem that the training material is predominantly English.)
For example, if I ask for a pasta recipe in Italian, will I get a more authentic recipe than in English?
I’m curious if anyone has done much experimenting with this concept.
Edit: I looked up Sapir-Whorf after writing. That’s not exactly where my theory started. I’m thinking more about vector embedding. I.e., the same content in different languages will end up with slightly different positions in vector space. How significantly might that influence the generated response?
More authentic, who knows? That's a tricky concept. I do think I'd like to try this robot-Italian recipe next time I make bolognese, though; the difference might be interesting.
I had some papers about this open earlier today but closed them so now I can't link them ;(
There should be a larger Armenian corpus out there. Do any other languages cause this issue? Translation is a real killer app for LLMs, surprised to see this problem in 2026.
Nonetheless ragù alla bolognese is made with ground beef and tomato sauce, so the italian version is simply wrong. Try and ask for ragù recipe instead. :)
I often consult several different versions of a recipe before cooking, and this feels like a normal degree of variation. Perhaps there are regional differences?
Just for kicks, I asked (in English) "what is an authentic Italian recipe for bolognese ragu?", and it produced a recipe similar to the version returned from the Italian prompt, noting "This version follows the classic canon recognized by the Accademia Italiana della Cucina". Searching on name of that organization led me to this recipe:
https://www.accademiaitalianadellacucina.it/sites/default/fi...
There are indeed regional differences, but at that point is not called "alla bolognese" anymore but "alla whatever place". People usually call it "ragù" and that's it.
Didn't know that the original recipe has pancetta too. It's good nonetheless. :)
The texture was way better. It's a pain to do (obviously) but worth trying at least once, IMO.
I ended up chopping it down to 2-3mm (~1/8in?) bits, and it helps to have the meat really cold (eg having hung out in the freezer for a bit).
I promise to use it in English as soon as Germany becomes Deutschland and Japan becomes Nippon.
First responders and medical professionals famously often have a sense of humor too dark to use around outsiders without causing offence/outrage(like what happened here), but I'm quite sure they are not "making light" of the loss of life and terrible injuries they face and fight.
No, saying that the Armenian genocide wasn't just "ethnic cleansing" isn't "a great example of whataboutism."
You're free to call Japan Nippon as long as you're fine with people raising eyebrows, sometimes not understanding what you mean, or deciding you're a pretentious twit.
The request that we use a character that doesn't even exist in the English alphabet (ü) is particularly ludicrous.
It would make even more sense, after all we lose letters because we write those sounds using other letters or letter combinations, however the "ü" in "Türkiye" doesn't have an analogue in the existing alphabet.
If you're arguing in good faith, you need to take about three steps back and realize what caliber of strawman you're fighting against here.
Like three times in this conversation I've explicitly differentiated between 'making jokes about' and 'downplaying' something, and every time you have failed to engage with my reasoning and instead chosen to simply double down on your two-dimensional accusation.
No, but not engaging with my argument supporting my position(about the emergency workers, though if your point is about this specific joke and not jokes about taboo topics in general I'll admit that that is moot), and setting up strawmen("about how the Holocaust wasn’t so bad?") means you're not arguing in good faith.
This isn't a discussion, you're just yelling your opinion at me over and over.
That jogged me a little: The magnitude of the issue would be different in the mind of any person: The original poster of the joke and I see more of a historical fact and engage with it fairly casually, while someone very directly affected might still (I maintain, though you don't have to agree) make jokes about it, but a very different kind of joke, one that does include the seriousness of the issue to them.
I'm having a little trouble articulating it, but I think my point is: You were "right" to call out the original joke as coming from a place of not-as-serious-about-the-genocide as, well, you seem to be. But this is a function of us, the people who indeed are not as serious about it as those more closely affected, not of it being a joke.