Re:What thousands of conversations look like inside a langua...
by rustyhancock on Sunday November 15, 2026 @07:52AM
(#50506591)
I wish there had been a third broad language style such as arabic although perhaps Qwen doesnt use arabic.
It made me think what if totally different knowledge bases could exist in a model where as my mental model was similar to OPs translation from pure knowledge source.
It also explains why rewriring prompts to another language sometimes lets you bypass restrictions.
Re:What thousands of conversations look like inside a langua...
by mcswell on Sunday November 15, 2026 @01:06PM
(#50509138)
Also, Arabic script is used for a number of non-Arabic languages, including Urdu and Farsi (Persian). It would be interesting to see if the projections of those languages have similarities as a group to the group using Latin script.
Another interesting (to me) comparison would be between Hindi (using Devanagri) and Urdu (using Arabic script). The two languages are very closely related, being largely mutually intelligible in their spoken forms.
Re:What thousands of conversations look like inside a langua...
by Scene_Cast2 on Sunday November 15, 2026 @08:46AM
(#50506916)
The methodology feels either heavily undercooked to the point of being misleading, or heavily under explained. Why are we in 3D? At which point did dimensionality reduction hit? And if we're doing dimensionality reduction, does the "plane" really mean anything?
Re:What thousands of conversations look like inside a langua...
by vhold on Sunday November 15, 2026 @08:59AM
(#50506987)
It's under explained. It's in 3D because of PCA. It mentions PCA all over the place, but never even says what it is, less alone briefly describe what it does.
There are a lot of more fancy ways to reduce dimensions and create visualizations like these that tend to preserve more of the higher dimensional structure.
Re:What thousands of conversations look like inside a langua...
by Scene_Cast2 on Sunday November 15, 2026 @09:11AM
(#50507063)
I'm very familiar with PCA. There are so, so many ways you can apply it to this problem.
Assuming the simplest interpretation of what the analysis did, then it's saying "the variance of the biggest variance direction stays constant". Which in itself is an interesting thread to tug on, but the charts aren't how you'd present such a result.
Re:What thousands of conversations look like inside a langua...
by oldjohnnylane on Sunday November 15, 2026 @10:18AM
(#50507521)
There’s no meat here. It’s just someone throwing data into a plotting tool with no meaningful results or conclusions. I was expecting a meaningful analysis. Nope.
Re:What thousands of conversations look like inside a langua...
by deepsquirrelnet on Sunday November 15, 2026 @10:44AM
(#50507787)
About a year ago, I made a very simple language detection model from the token embedding tensor of gemma 3. I used UMAP to show the projections of how languages separated into a 2D space. It's very interesting to look at IMO.
Re:What thousands of conversations look like inside a langua...
by plagiarist on Sunday November 15, 2026 @10:05AM
(#50507430)
This is an interesting idea, do you find it has more interesting properties than doing cosine similarly by reviewers? Have you found things adjacent to games you enjoyed that were also fun to play?
Re:What thousands of conversations look like inside a langua...
by plagiarist on Sunday November 15, 2026 @03:29PM
(#50510374)
That original idea also sounds interesting to me, if you modified it to work in a semantic space where "beautiful" and "not beautiful" differed by more. Write a hypothetical review and it finds the closest match. It's a very cool project, thank you for sharing this with us.
was one of very few useful results of the first decade of TREC research... And the main thing it addresses is balancing various factors which could cause a full text search engine to privilege either long or short documents.
Re:What thousands of conversations look like inside a langua...
by Joel_Mckay on Sunday November 15, 2026 @11:58AM
(#50508460)
In general, ranking relevant keywords in the context of the Negative reviews will likely have more hits the longer people complain.
The random fluctuations of individual experience only cancel out bias if and only if the results are truly unbiased normal distributions.
In the case of positive:negative ratio feedback scoring, it only makes sense if you ignore the entire message body of what people enjoyed.
Negative-weighted ratio ranking more accurately describes the end users experience. Any game with paying unique customer greifer total scores under 15% without game-play reliability related complaint keywords is going to be a fairly good game if the genre matches your profile preferences.
Otherwise, people will just see shit scores from the response bias of pissed off users on dodgy OS/Networks. Would recommend checking your conclusions with the average current active players in the SteamDB plugin. If users aren't engaged with the paid gameplay experience 6 months after launch, than the release likely isn't fun or broken garbage. =3
A good game, but takes some skill to play (4270 daily players 10 years later):
Re:What thousands of conversations look like inside a langua...
by tomaskafka on Sunday November 15, 2026 @11:59AM
(#50508475)
I have played with similar problem in different domain, and if you could have “which users play which games” (or in general “which articles are read by which people”), you can do really good similarity search and self organizing map based on no content at all, just the metadata.
Which is of course why Facebook can say they don’t read your conversation content, while still be able to target ads precisely based on conversion metadata.
Re:What thousands of conversations look like inside a langua...
by Roxxik on Sunday November 15, 2026 @02:09PM
(#50509695)
Not sure how related the cause is, but the fix seems to apply too.
In single cell genomics you often have a large correlation between the data and the length of the sequencing reads.
You can calculate the correlation between your embeddings and every PC dimension and exclude the highly correlating dimensions before doing the umap. Similar can be done for other metrics. I've seen it done for patient gender for example. I could imagine looking at the correlation for publish year or genre.
Re:What thousands of conversations look like inside a langua...
by jrmg on Sunday November 15, 2026 @10:38AM
(#50507732)
Naive question:
This is visualizing end states, right? That’s why there are no ‘paths’ between the orange initial cloud and the ‘result’ clouds?
Wouldn’t we expect the languages to be ‘separate’ by that point? The output is necessarily different after all - and ‘more different’ for Chinese and English than for other Latin script languages and English.
It feels like it would be more interesting to see the intermediate states. Do questions about the same topics in Chinese and English ‘traverse’ similar areas in the vector space?
Re:What thousands of conversations look like inside a langua...
by supermatt on Sunday November 15, 2026 @11:48AM
(#50508370)
Isn’t this last layer analysis basically saying that after a bunch of Chinese tokens you get a Chinese token, and after some Latin tokens you get a Latin token? That seems expected given the setup. Would be interested in seeing what translations look like in the middle layers.
Re:What thousands of conversations look like inside a langua...
by Sophira on Sunday November 15, 2026 @04:49PM
(#50511191)
I'm just a layperson in this field, but I'm wondering if part of the reason for the separation could be the cultural expectations set by the language.
After all, to be able to understand a question being asked, you have to understand the culture that it's presented within, and in a lot of cases, being asked a question in a specific language tells you what cultural expectations that person has... and a lot of people tend to think of "Western culture" as a homogenous blob.
Of course, it could also be simple that all of the tested languages, apart from Chinese, use the Latin alphabet. I have no idea, I'm just throwing out ideas here.
It would be interesting to see how, say, Swahili (as a language that uses the Latin alphabet but whose cultural heritage is distinct from "Western culture") compares here.
It made me think what if totally different knowledge bases could exist in a model where as my mental model was similar to OPs translation from pure knowledge source.
It also explains why rewriring prompts to another language sometimes lets you bypass restrictions.
Another interesting (to me) comparison would be between Hindi (using Devanagri) and Urdu (using Arabic script). The two languages are very closely related, being largely mutually intelligible in their spoken forms.
https://en.wikipedia.org/wiki/Principal_component_analysis
There are a lot of more fancy ways to reduce dimensions and create visualizations like these that tend to preserve more of the higher dimensional structure.
Here's a semi recent paper discussing and comparing some of them, I didn't dig too deep to try to find a more recent or better one : https://pmc.ncbi.nlm.nih.gov/articles/PMC12453773/
Assuming the simplest interpretation of what the analysis did, then it's saying "the variance of the biggest variance direction stays constant". Which in itself is an interesting thread to tug on, but the charts aren't how you'd present such a result.
Isn’t there an obvious answer to this? It’s about visualization. There’s a natural upper limit to dimensions we can see, and 3 is where we hit it.
https://huggingface.co/blog/dleemiller/wordllama-detect
If you just want to see the plot directly: https://cdn-uploads.huggingface.co/production/uploads/65ff92...
https://en.wikipedia.org/wiki/Okapi_BM25
was one of very few useful results of the first decade of TREC research... And the main thing it addresses is balancing various factors which could cause a full text search engine to privilege either long or short documents.
The random fluctuations of individual experience only cancel out bias if and only if the results are truly unbiased normal distributions.
In the case of positive:negative ratio feedback scoring, it only makes sense if you ignore the entire message body of what people enjoyed.
Negative-weighted ratio ranking more accurately describes the end users experience. Any game with paying unique customer greifer total scores under 15% without game-play reliability related complaint keywords is going to be a fairly good game if the genre matches your profile preferences.
Otherwise, people will just see shit scores from the response bias of pissed off users on dodgy OS/Networks. Would recommend checking your conclusions with the average current active players in the SteamDB plugin. If users aren't engaged with the paid gameplay experience 6 months after launch, than the release likely isn't fun or broken garbage. =3
A good game, but takes some skill to play (4270 daily players 10 years later):
https://store.steampowered.com/app/219990/Grim_Dawn/
A similar genre game, but people score it higher (3650 daily players 1 year later):
https://store.steampowered.com/app/1145350/Hades_II/
Which is of course why Facebook can say they don’t read your conversation content, while still be able to target ads precisely based on conversion metadata.
In single cell genomics you often have a large correlation between the data and the length of the sequencing reads.
You can calculate the correlation between your embeddings and every PC dimension and exclude the highly correlating dimensions before doing the umap. Similar can be done for other metrics. I've seen it done for patient gender for example. I could imagine looking at the correlation for publish year or genre.
This is visualizing end states, right? That’s why there are no ‘paths’ between the orange initial cloud and the ‘result’ clouds?
Wouldn’t we expect the languages to be ‘separate’ by that point? The output is necessarily different after all - and ‘more different’ for Chinese and English than for other Latin script languages and English.
It feels like it would be more interesting to see the intermediate states. Do questions about the same topics in Chinese and English ‘traverse’ similar areas in the vector space?
Am I completely misunderstanding?…
Definitive and undeniably digestible proof for linguistic relativity in a single picture?
Or something else a lot less controversial? Are there other visualizations that bunch of things cluster apart beautifully like the olympic games flag?
After all, to be able to understand a question being asked, you have to understand the culture that it's presented within, and in a lot of cases, being asked a question in a specific language tells you what cultural expectations that person has... and a lot of people tend to think of "Western culture" as a homogenous blob.
Of course, it could also be simple that all of the tested languages, apart from Chinese, use the Latin alphabet. I have no idea, I'm just throwing out ideas here.
It would be interesting to see how, say, Swahili (as a language that uses the Latin alphabet but whose cultural heritage is distinct from "Western culture") compares here.