Ten minutes ago (at around 17:15 p.m. Japan time), NHK was reporting that there were many emergency calls coming in from Uki City, where shindo 7 was recorded, but that the extent of the damage or injuries was not yet known.

There have also been many aftershocks, including some strong ones, and tsunami warnings.

[1] https://www.jma.go.jp/jma/en/Activities/jishintsunami/jishin...

JCII Camera Museum https://www.jcii-cameramuseum.jp/top-e/

Small Worlds Miniature Museum https://smallworlds.jp/en/

Button Museum https://button-museum.jp/en/

World Bags and Luggage Museum https://www.ace.jp/en/museum/

Meguro Parasitological Museum https://www.kiseichu.org/e-top

I learned about the Button Museum more than twenty-five years ago. I was taking a walk along the Sumida River and noticed two big buttons on a sign overlooking the river:

https://www.google.com/maps/@35.691592,139.7887136,2a,15y,24...

Haven’t visit the museum yet, though.

https://gally.net/temp/20260701_Fable_synthesizer_2_with_pro...

I then gave that full prompt to Fable in Claude Code. Here is the result:

https://gally.net/temp/20260701_Fable_synthesizer_2_with_pro...

For the second, I just gave a short prompt [1] directly to Fable in Claude Code. Here is that result:

https://gally.net/temp/20260701_Fable_synthesizer_3_with_dir...

I can’t say that one is better than the other; that would take a lot more tests, and the judgments would be pretty subjective in any case.

Both were completely one-shot. Last year, when I was doing similar tests with various models, the synthesizers rarely worked right on the first shot, and I would have to do some back-and-forth to get them functioning. This time, Fable was able to open the files in Chrome itself, view and adjust the page layout, and monitor the browser events for errors. Each time it made some adjustments to the file. The only thing it wasn’t able to do was listen to and assess the sounds produced.

[1] “Write a browser-based synthesizer for me. The synthesizer should automatically create interesting polyphonic music in which the various voices play off against each other in both harmony and contrast. The controls will affect the tone, rhythmic patterns, number of voices, complexity and randomness of the melodies, and other features. The controlled features should be original—not just standard synthesizer functions—and encourage creative explorations even by naive users.”

I should mention that Fable also did an impressive job on a couple of major project-redesign tasks I gave it. Those aren't things I can share here, though.

“I want to ask Claude Code to write a browser-based synthesizer for me. Please prepare a prompt for it that I can give to it for it to write the synthesizer. The synthesizer should automatically create interesting polyphonic music in which the various voices play off against each other in both harmony and contrast. The controls will affect the tone, rhythmic patterns, number of voices, complexity and randomness of the melodies, and other features. The controlled features should be original—not just standard synthesizer functions—and encourage creative explorations even by naive users. So write a prompt that I can give to Claude Code to create that synthesizer.”

I then gave the prompt produced by Opus to Fable in Claude Code.

Last year, I would occasionally test the latest models by vibe-coding in-browser music generators using only HTML, CSS, and JS. Here’s one made in July by Gemini:

https://gally.net/temp/20250701synthesizer-gemini2/index.htm...

And one made in September by Claude:

https://gally.net/temp/20250917rhythmdrone/index.html

With Fable, I was able to one-shot something much more sophisticated:

https://gally.net/temp/20260610-fable-synthesizer/index.html

It’s still a long way from creating music I would want to listen to, though.

Comments URL: https://news.ycombinator.com/item?id=48598948

Points: 2

# Comments: 0

https://news.ycombinator.com/item?id=48510010

She writes: “I adapt, I localize, and I find the best way to convey the original message so it makes sense and feels natural. I research terminology. I make sure it’s consistent throughout.”

I’m sure she has other important insights into what enables her to do her job well. The problem is whether or not such insights can be incorporated into an AI-driven translation system, too.

Since early this year, I have been experimenting with a variety of agentic systems for language-related tasks, including dictionary-writing, research on topics in the philosophy of language, essay-writing, and translation. Other than the dictionary [1], I am keeping the results private, so they haven’t been evaluated by others. But my personal assessment is that agentic systems given suitable high-level guidance can be very good at such tasks now.

If I were still freelancing and I had a large translation job to do for a client, here is the outline of the prompt I would give to Claude to get it started:

“Use this private GitHub repository to build a system for translating [genre of text] from [Language1] to [Language2]. The directory samples/ contains examples of the type of document to be translated, high-quality human translations of those documents, and texts in [Language2] that are in writing styles that I believe to be appropriate for this genre of translation. The file guidelines.md contains my general instructions about the needs of my client and my preferences for how you should translate texts along various axes (natural vs. literal, informal vs. formal, preferred dialect in [Language2], consistency vs. variety in terminology translation, etc.). Begin building (1) a knowledge wiki for this project using Karpathy’s LLM-wiki framework and (2) a system inspired by Karpathy’s Autoresearch, AutoResearchClaw, etc. for testing and recursively improving both the functioning of the system and the quality of the translations. For the actual translation, editing, checking, etc., use not only your own ability and the knowledge assembled in (1) but also outsource such tasks to other frontier models through OpenRouter, and use adversarial evaluations among those models and yourself to check and recursively improve the system design, the prompt-writing for other models, and any translations created by the system. My OpenRouter API key is available in this environment. You may spend up to $xx per day in API calls until this project is ready to do real translations; before beginning a real job, give me an estimate for how much the API calls will cost for that job. The initial build-out of this project will take many sessions, so write a prompt called resume-prompt.md that I can point you to at the start of a scheduled Routine to have you work on this. Commit and squash-merge to main at the end of each session. I will be checking in occasionally to view your progress and to ask you to run translation tests, and I will offer guidance then on how to improve the pipeline further and make the translations closer to what my client needs. If you have any questions before you begin, please ask me.”

[1] https://www.tkgje.jp

But the neural models were still not translating meaning, which is the whole point of translation. I devised a variety of tests to see if GT could identify the meaning of ambiguous words from the context, and it couldn’t. One example I would show people was the sentences “I was born in 1998, and my sister was born in 1999” and “I was born in 1999, and my sister was born in 1998” translated into Japanese. Japanese uses different words for older and younger siblings, but GT translated “my sister” with the same word in both sentences. It was easy to come up with other examples where GT would fail, such as when the meaning of a word could only be determined based on context in a previous sentence; at that time, GT seemed to be translating sentence-by-sentence, with no consideration of what came before or after. I kept waiting to see whether computers would ever be able to handle meaning when translating, and for years thereafter there was little progress.

A minor shock came in mid-2022, when DALL-E 2 was released. Its ability to create images from natural-language prompts suggested that something deeper was going on than just statistical correlations. But I couldn’t see yet what the useful applications might be.

My biggest “oh shit” moment came with ChatGPT in late 2022. While the initial release didn’t translate Japanese well (I seem to recall that there were character-encoding issues), I ran various tests to see if it could, for example, identify the antecedents of pronouns and the meanings of polysemous words in English based on the context. It did really well. Last December, I gave a talk at a university in Tokyo in which I showed some examples done with the 2022-era GPT-3.5. They appear in slides 4 to 8 of the following:

https://www.gally.net/miscellaneous/20251206_Gally_ICU_slide...

There have been a lot of “oh shit” moments for me since, especially after the release of reasoning models and, now, long-running agents.

This was all before LLMs. The assumptions behind my class have since been upended, now that easily available chatbots can produce academic writing that, at least at the structural level, is perfectly fine.

I agree, but it’s worth noting that that has been done since long before LLMs. Fifteen years ago, I used to teach a graduate course on academic writing pedagogy. The students and I would read research papers on the teaching of academic writing; we also analyzed textbooks and course syllabuses to get an idea about what was actually being done in classrooms. While phrases like “critical thinking” did come up, the overall focus was clearly on language patterns: sentence and paragraph structure, the use of transition words, vocabulary for hedging and boosting (i.e., making assertions seem weaker or stronger), etc.

In a university context, it can be very difficult to evaluate student writing based on its content. In humanities-focused and creative writing, what the student decides to say can be seen as an extension of the student’s personality, identity, and individual experience; if a teacher evaluates the content, including the reasoning, it can seem that the teacher is evaluating the student as a person. And if the students are in the sciences, especially at the graduate level, the writing teacher often won’t even understand what the students write because it is too technical. Teaching and evaluating language patterns, not content, is often the only option.

Comments URL: https://news.ycombinator.com/item?id=48333587

Points: 2

# Comments: 0

Since January, I’ve been having Claude build a static Japanese-English dictionary in which all of the kanji and jukugo can be displayed either with or without furigana:

https://www.tkgje.jp/index.html

I haven’t spotted any mistakes in the furigana myself, though there must be some. I have a scheduled routine running multiple times a day to have Claude check and polish existing entries; it should be correcting most of whatever furigana mistakes might be in the data. At some point, I will set up an agent to use a different LLM to run a similar set of checks to try to reduce the error rate even more.

As you note, the readings of Japanese words depend on the context, so producing accurate furigana cannot be done entirely programmatically. Sentences must be interpreted semantically.

I am releasing all of the dictionary data into the public domain, and anyone is free to fork it or adapt it however they like:

https://github.com/tkgally/je-dict-1

https://gally.net/temp/20260525_LLM_random_numbers/index.htm...

This experiment cost a total of US$0.0454 through OpenRouter.

Here's an example wiki in a public repository for a dictionary I have been having Claude build for the past few months:

https://github.com/tkgally/je-dict-1/blob/main/planning/wiki...

I have to consciously avoid using AI for more cognitive tasks, though. It would be very tempting to have Claude, ChatGPT, or Gemini summarize, classify, and grade the students’ assignments, write individual feedback, prepare my lesson plans, etc. However, I know that my engagement with the material and with the students would suffer. I also want to show the students that they are learning together with me and with each other, not with bots.

I am semiretired and have a light teaching load that gives me plenty of time to prepare for class. I can see that full-time teachers might find it hard to resist the lure of offloading their thinking to AI.