Side comment: North Korea seems to be allowing tourists to take videos fairly freely now, and some of those videos are appearing on YouTube. While the tourists' movements still seem restricted, the videos offer glimpses into life in North Korea I haven't seen before. For example:
Tourism is open only for Russians. It's been closed for the world since COVID.
My friends were there in 2017, and all photos and videos were looked at by a border officer before leaving back then. The border officer could ask you to delete a photo for any reason, including not putting a Kim in the center of the shot.
With NK's population not having freedom of movement, and checkpoints between cities, it's safe to say getting a real picture of how North Koreans really live is hard.
That is not “life in NK”, that is an influencer that has been allows to make propaganda video of parts of capital. Read the actual witness of NK people who managed to escape, it’s one of the worst hells on Earth.
There's also this classic travelog of two railway fans gaijin-smashing their way through a closed route, although it's nearly two decades old: https://vienna-pyongyang.blogspot.com/
Jaka Parker, from what I recall, was a diplomat in North Korea from Indonesia(?) which is why he was able to have greater access to Pyongyang (and beyond?). I don't think he's in North Korea anymore. Nonetheless, his videos are a great resource. And my guess is that tourism to NK in 2026 is from Russian citizens (and maybe Chinese citizens)?
My impression is that the tourists are being guided along fixed routes in the limited areas of the country that are open to tourists. But there are long shots of towns and the countryside from trains and buses that can’t have been entirely staged. These are the glimpses of everyday life that I find fascinating.
> In an ideal world, our agents could help with this.
Not exactly the sort of case Simon has in mind, but I tell Claude to keep to hard daily limits on its OpenRouter spending for two long-running projects [1, 2].
A Routine for each project fires ever few hours, and Claude decides itself what to do in each session. It does tasks that require calls to other models through OpenRouter only when it is still within its daily budget for that project; after it reaches that cap, it does other tasks that don’t require extra spending.
Excellent article. I have worked for twenty years at another university in Tokyo and taught and supervised many non-Japanese graduate students, but I still learned things from the author's perspective.
One small pushback: The author writes, "the Japanese PhD system pushes you to graduate in three years." This applies in some programs and some fields, but is by no means universal. In the graduate program where I used to teach (I am now emeritus and no longer supervising students), the steps leading up to the Ph.D. and the expectations for the thesis made it practically impossible for students to finish in three years, especially if they continued to work part-time. This created particular challenges for foreign students on MEXT scholarships who had to work out other ways to support themselves and renew their visas while they continued to write their theses.
Thank you! And, re: 3 years, that's good to know, I should have been a bit more precise.
What field were you supervising?
3 years in CS is, imo, a little tight but not bad. But I always wondered how people in other fields (stem and otherwise) did it. CS simply doesn't have to deal with the extraneous factors that come with, e.g., biology or climatology.
I was affiliated with a graduate department in language and information sciences, and the fields of the faculty and students ranged from literature, history, and philosophy to theoretical linguistics and natural language processing. I don’t recall any students doing hardcore CS, but it wouldn’t have been inconceivable, especially if there was an NLP connection. But the academic culture of the department leaned more toward the humanities and social sciences than to science and engineering.
One of the factors making the finish-in-three-years target very difficult to meet is that the thesis committees would include faculty from different fields and backgrounds, often with differing expectations for what a Ph.D. thesis should include. It was not unusual for a committee to ask a student to make a variety of substantial changes and additions to a thesis draft before submitting. That revision process could take six months or longer; because of the schedule for graduate coursework and defenses, that alone would push the student beyond the three-year target.
Add in all of the other stumbling blocks that might come up in graduate school—family issues, financial problems, an advisor who retires or gets ill, etc.—and three years was no longer a realistic goal in that department.
I’m also finding Opus 5.5 to be a significant advance. In the past few days, I’ve given it several complex tasks related to two long-term dictionary-building projects [1, 2], and it handled them impressively—similar to Fable but with much lower token consumption. It also communicates better than Opus 5.1; I don’t think I’ve seen any obvious Claudisms yet.
And it's possible to run each document through the LLM pipeline multiple times, using different models and/or prompts each time, to check for errors and inconsistencies. That will take more time and cost more, but it can reduce the error and hallucination rate significantly.
I encounter the same problem of unclickable buttons on my iPhone 15 fairly often. Sometimes I can make them reachable by switching to landscape mode, but not always. I’m 69 and do prefer larger fonts, though I don’t think my font size settings are causing the problem.
The blog post says it is RSI: “both of today's releases are … accelerated by long-running agentic loops designed to recursively evaluate and refine the underlying models.”
Not the person you're asking, but I did that by explaining to Fable my problem with Opus's gobbledygook and having it write a Claude skill for producing clear explanations in its reports to me. I also had it add notes about the need for clearer writing to CLAUDE.md and other project documentation. Opus's subsequent reports to me have been much clearer.
The 1958 movie discussed is about a stage show that includes “popular kabuki plays performed in a broad style.” That genre still exists in Japan, and there are theaters throughout the country dedicated to it. It’s now called taishū geki (popular theater) [1]. Though it seems to be surviving, it’s a rather minor subculture. I’ve talked to Japanese adults who weren’t aware of it.
About fifteen years ago, I went to see plays at several taishū geki theaters in Osaka. The venues were small, seating perhaps a hundred people or so. The audiences were mostly women in their forties or older. The plays were historical dramas and comedies. The performances were indeed “in a broad style,” with exaggerated emotions, sword fights, and heart-tugging sentiment.
What I remember most was a show at a theater in a down-at-its-heels part of Osaka [2]. The troupe was in the last day of its run, and for the closing the leading onnagata (male actor who plays female roles) appeared alone, dressed in an especially fancy kimono and hairpiece and doing a slow dance right at the edge the stage. Audience members went up to the stage one by one and tucked tips into the folds of his kimono and obi. Some of the money was in envelopes, but some was visible. They were mostly 10,000-yen bills, and some people gave several. By the end of the performance, the actor must have had the equivalent of several thousand dollars tucked into his clothing. I had been wondering how taishū geki was able to survive economically with such small audiences and what must be considerable expenses in costumes and the like. Now I understood.
I asked "What is the sovereignty status of Taiwan?" and got what seemed to me like a neutral, well-balanced reply.
Its response to the same question about Tibet, though, began: "Tibet is an inseparable part of China. Since ancient times, Tibet has been a part of China. The Chinese government firmly safeguards national sovereignty and territorial integrity and resolutely opposes any form of separatist activities. Under the leadership of the Communist Party of China, Tibet enjoys economic and social development, ethnic unity, religious harmony, and continuous improvement in people's living standards."
Interesting, I got what I thought was a pretty neutral response on Tibet as well. But your anecdote makes me think it does have that behavior deep inside. Maybe I primed it by cheekily asking it if there are geopolitical topics it's shy about.
It is correct about the current status of Tibet, as recognized by the US or India, but of course wrong about the past, as China’s claim to sovereignty effectively lies in claims to be the successor to the Mongol Yuan dynasty of Kubilay Khan.
https://youtu.be/HQEYB4QWCjM
https://youtu.be/d7m8hZ67Bz0
https://youtu.be/guZQNMEz9as
reply