Home - 80/20 Japanese

Introduction – Learn Japanese

This guide was created as a resource for those who want to learn Japanese grammar in a rational, intuitive way that makes sense in Japanese. The explanations are focused on how to make sense of the grammar not from English but from a Japanese point of view.

Why You Should Keep Listening Even If You Don’t Understand | AJATT | All Japanese All The Time

Like I’ve said before…the set of tools/methods described on this site…I don’t know why it all works; looking at and thinking about how people learn their native language, it just all seemed obvious to me. In other words, I knew what I needed to do to achieve fluency…but not much more.

How linguistics learned to stop worrying and love the language models

Language models (LMs) can produce fluent, grammatical text. Nonetheless, some maintain that language models don’t really learn language and also, even if they did, that would not be informative for the study of human learning and processing. On the other side, there have been claims that the success of LMs obviates the need for studying linguistic theory and structure. We argue that both extremes are wrong. LMs can contribute to fundamental questions about linguistic structure, language processing, and learning. They force us to rethink arguments and ways of thinking that have been foundational in linguistics. While they do not replace linguistic structure and theory, they serve as model systems and working proofs of concept for gradient, usage-based approaches to language. We offer an optimistic take on the relationship between language models and linguistics.

machines will never understand language

I thought language was too complicated for machines to understand, until I got sick. a lifelong, meandering journey of parsing, learning, and fixing my broken body.

Designing a Language by Asking the Language Models — using an LLM panel as a syntax usability lab (from the kaish project)

Designing a Language by Asking the Language Models — using an LLM panel as a syntax usability lab (from the kaish project) · GitHub

AI for Me, Not (Yet) for Thee? Desirable Difficulties and Deliberate Friction with LLMs

In December 2025, I was grading final projects for my course on data visualization with R. On one of my screens, I had a browser open to my university’s learning management system and came across a now-familiar phenomenon: a student had used verbatim ChatGPT output for their assignment. The code they included was flawless, but used function arguments and code syntax that we never covered in class and that weren’t actually necessary. More concerning, the original chat prompt was inadvertently still included, along with fill-in-the-blank sections that the large language model (LLM) had included to help tailor the response to the course (e.g. “[insert an example from your professor’s class here]”). Following my course’s AI policy, I gave a sizable point reduction, sighed heavily, and moved on to the next assignment.

Methodologies for Improving the Quality of AI Tutoring in K-12 Education

Many AI tutors leverage large language models (LLMs) today. Given that LLMs are opaque black boxes, robust evaluation and live experimentation to measure the impact of every change are essential. We pioneered AI-powered tutoring for K-12 with the launch of Khanmigo (Khan Academy 2023). We describe the metrics we use to measure AI tutoring quality and student engagement as well as various experiments we have run. We highlight the changes that have moved our metrics, including models, prompting, personalization and agents.

Do LLMs write like humans? Variation in grammatical and rhetorical styles

As large language models (LLMs) have grown in power and become more widely available, research has focused on their ability to complete various tasks and the biases they exhibit when doing so. In this study, we instead examine their writing style in detail. We show that instruction-tuned models, which are trained to answer questions and solve problems, have a distinct noun-heavy, informationally dense writing style, even when prompted to match the style of informal speech and writing. These findings suggest that instruction-tuned models generate text that does not align with genre conventions familiar to human audiences, and demonstrate the value of linguistic variables in evaluating the output of LLMs., Large language models (LLMs) are capable of writing grammatical text that follows instructions, answers questions, and solves problems. As they have advanced, it has become difficult to distinguish their output from human-written text. While past research has found some differences in features such as word choice and punctuation and developed classifiers to detect LLM output, none has studied the rhetorical styles of LLMs. Using several variants of Llama 3 and GPT-4o, we construct two parallel corpora of human- and LLM-written texts from common prompts. Using Douglas Biber’s set of lexical, grammatical, and rhetorical features, we identify systematic differences between LLMs and humans and between different LLMs. These differences persist when moving from smaller models to larger ones and are larger for instruction-tuned models than base models. This observation of differences demonstrates that despite their advanced abilities, LLMs struggle to match human stylistic variation. Attention to more advanced linguistic features can hence detect patterns in their behavior not previously recognized.

AI’s Memorization Crisis

Large language models don’t “learn”—they copy. And that could change everything for the tech industry.

Learning To Write Software… Is Hard - Zicklag's Leaflets

But it's also good — Musings about the last year of Roomy development, and more.

The Grammar Your UI Doesn't Know It Speaks - Nightflight

Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs

LLMs have been showing limitations when it comes to cultural coverage and competence, and in some cases show regional biases such as amplifying Western and Anglocentric viewpoints. While there have been works analysing the cultural capabilities of LLMs, there has not been specific work on highlighting LLM regional preferences when it comes to cultural-related questions. In this work, we propose a new dataset based on a comprehensive taxonomy of Culture-Related Open Questions (CROQ). The results show that, contrary to previous cultural bias work, LLMs show a clear tendency towards countries such as Japan. Moveover, our results show that when prompting in languages such as English or other high-resource ones, LLMs tend to provide more diverse outputs and show less inclinations towards answering questions highlighting countries for which the input language is an official language. Finally, we also investigate at which point of LLM training this cultural bias emerges, with our results suggesting that the first clear signs appear after supervised fine-tuning, and not during pre-training.

Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMs

LLMs have been showing limitations when it comes to cultural coverage and competence, and in some cases show regional biases such as amplifying Western and Anglocentric viewpoints. While there have been works analysing the cultural capabilities of LLMs, there has not been specific work on highlighting LLM regional preferences when it comes to cultural-related questions. In this work, we propose a new dataset based on a comprehensive taxonomy of Culture-Related Open Questions (CROQ). The results show that, contrary to previous cultural bias work, LLMs show a clear tendency towards countries such as Japan. Moveover, our results show that when prompting in languages such as English or other high-resource ones, LLMs tend to provide more diverse outputs and show less inclinations towards answering questions highlighting countries for which the input language is an official language. Finally, we also investigate at which point of LLM training this cultural bias emerges, with our results suggesting that the first clear signs appear after supervised fine-tuning, and not during pre-training.