Reader

A short list of some stuff I've put together for personal use using AI coding.

Writing Tutor

A writing tutor for my kids, based on the Hochman Method, which walks them through construction of sentences, paragraphs, and so on.

Jeeves bot

A bot that sends me a daily synopsis of events, workouts, and the weather. Currently the only interactive element is a flow where I can add/remove/change the workouts for today or tomorrow that are planned in my intervals.icu account.

Tulay language bridge

“Tulay” means “bridge” in Tagalog, which I'm trying to learn. The app pulls information from my LingQ account and my Anki decks to create a master list of all words I know so far and what their status is. From there, I can generate mnemonics, for example for the word alagang, which means pet, it generated this mnemonic story:

all a gang — In a sunny yard, a whole gang of puppies and kittens crowds around you, licking your hands—every single one is your pet, and you laugh, 'All a gang? Yes, all a gang of beloved pets!'

This helps anchor the word in a funny story and aids in memorization.

Then based on the mnemonic, it generates 3 sentences which use at least 80% words I already know, and formats them into cloze cards in Anki, and syncs them to my deck.

Each morning, the app sends me a notification (via web browser notifications) with a ~100 word story that contains 80-90% words I already know, uploads it to LingQ as a lesson, and gives me the link. This pushes me to learn something new each day, beyond reviewing already known words.

A few unfinished things

• A surveillance system for my brother in law, he ended up using another programmer for it so I'm letting it go, but I might pick it back up when we move to a family compound in the province soon, as we'll have a need to collate surveillance feeds and make them actionable for us and our employees.
• A learning system for my kids for math. This ended up being a lot more complicated than I originally realized, so I kind of drifted away from it. The idea was to create a tree of all the Common Core math standards, with explicit dependency links between each standard, so if a student fails on a standard in a quiz, before re-teaching the standard, the system would first quiz all standards that one depends on, making sure there is no supporting information that is missing for the student. I have observed in my own kids that often a failed learning experience is not because of the information in front of them, it's because of a hidden assumption that they know something else or have fluency in something beyond what they have currently. For now I just have to do this manually by observing their results and intervening.

How I've been creating stuff

I've always struggled in the past with finishing personal projects. Typically I get a burst of inspiration that lasts a couple days, and in that time I can do an enormous amount of thinking and implementation, but before AI, I could only get so far before I hit some very annoying roadblock. Think like, I can't get my file permissions correct on my webserver, so I can't test the code I've written, so I'm stuck upgrading random packages and unwinding years of idiosyncratic setup on my VM. Then eventually I'd just run out of steam and drift away from that project.

With AI, that no longer happens. I just tell it what to do, and it does it. Even this blog was down for over 2 years because of simple issues that I just didn't want to deal with. I asked Cursor to fix it and it was done in 5 minutes, and I updated the WriteFreely instance to boot. In the past even that last step would have required hours of reading 2 years of release notes watching out for gotchas (Cursor time, 30 seconds), running migrations, probably getting stuck on some stupid stuff.

While writing this post, I added image hosting to my local WriteFreely instance, even though that feature has been unfinished in the official project for years.

So now, with AI, I can generate such a huge amount of code, I can actually complete things before my motivation shifts. It's a huge difference for me.

For models and tools, I use Gemini to plan stuff, and it's my daily driver “chat” tool usually as well. Then I take whatever that generated and add it to a new repo in Cursor, which I use because last October I signed up for the yearly plan that had unlimited “Auto” model mode, which is an incredible deal. I can do billions of tokens a month with no extra charge.

I have some stuff running in val.town but I plan to port it out to my personal Linode server (which I plan to move to a cheaper VPS eventually, maybe OVH). Some things I run on my home desktop and then tunnel out to the web via my Linode, like Tulay.

When I embed a model into an app, like the mnemonic generation in Tulay, I have been using Deepseek. The deepseek-v4-flash model is almost too cheap to meter at this point. I've used it for weeks and racked up less than $1 of charges so far. It's plenty smart enough for most things. It may even be good enough for coding, but I have that free Cursor usage so I just use that for now. I'll re-assess in October when my plan expires, I'd rather not be using an XAI product in the long run.

Tomorrow, a hurricane is set to reach landfall over Tampa, FL. The storm surge is forecast to be 10-15 feet in that area, and 5-10 feet across many other coastal cities like Cape Coral. This is in an area where people have built their homes along canals and in lowlands abutting the ocean.

In addition to that, there is the potential for 12 inches of rain at roughly the same time. 12 inches of rain in an area that was just inundated with rain from Hurricane Helene a few weeks ago. 12 inches of rain in an area with a lot of impervious surface coverage (as all of the US has due to overwhelming car dependence).

I hope the people of that area make it out in time, and do not stay out of stubbornness or conspiracy thinking.

Afterwards, I wonder what's going to happen? Will all the homes be rebuilt? At whose cost? How many times will this happen in the coming years as sea level rises and hurricanes become stronger?

There is no “adaptation” to 15 feet storm surges and 12 inches of rain. There is only fleeing the area. Right now it's for the short term. At what point will it have to become long term?

Parenting intelligent kids can be a unique challenge. On the surface, it might seem like a blessing—a child who excels in school, who is curious about the world, and who learns quickly. But underneath this apparent ease lie a lot of problems that can make these children quite difficult. Intelligent kids often face challenges precisely because of their intelligence.

When children become aware of their intelligence, they may develop a sense of superiority, leading to poor behavior toward peers and teachers. They may struggle to empathize with others who learn at a different pace, and their behavior can come across as dismissive or condescending. This type of arrogance can also lead to social isolation, as peers may not want to engage with someone who acts as if they are “above” everyone else. Some kids can learn the wrong lesson from this, and decide to slack off just to fit in.

Then there's boredom. School is structured to cater to the average student, and for intelligent kids, this can mean lessons are too easy, leading them to check out mentally. Boredom, in turn, can lead to a lack of motivation and procrastination—a feeling that, because they can get away with doing things at the last minute, there’s no real need to engage deeply. Over time, this mindset can prevent them from learning the value of hard work, leaving them ill-prepared for situations that require sustained effort.I know I had a huge shock when I got to college and suddenly realized that I was completely unprepared for the level of work that was required. I had enough intelligence that high school was largely easy – I did my homework in study hall, and could ace tests without special preparation. But in college? I was screwed – I had to read tons of material, develop new study habits like actually taking notes in class and drilling key concepts, and really start learning.

The common advice is to praise hard work rather than intelligence—to encourage children to see effort as the path to success rather than innate ability. But kids are perceptive, and intelligent kids, in particular, can often tell they are ahead of their peers. They know when things come easier to them, and simply being told, “Work hard,” may not resonate when they feel their natural ability is enough. You are telling them one thing, but they are experiencing something different. If anything this could lead to them not trusting your judgment!

If we accept that intelligent children will realize their own capabilities, the question becomes: how do we guide them in a way that helps them develop resilience and empathy? One possible approach is exposing them to individuals who are even more capable, whether in person or through parasocial means like YouTube videos, books, or other media. By seeing people who excel beyond their current abilities, they can learn humility and gain perspective on how much they still have to learn.

Another approach is to provide them with more challenges—activities or projects that push them beyond what they’re used to. Parents, who are typically more intelligent than their children (at least until a certain age), can challenge their kids directly. However, this can create a tension when it comes to schooling. If a child is pushed far beyond their grade level at home, school may feel even less relevant, worsening the issue of boredom. This could lead to a situation where the child simply coasts through their school years, again missing out on the opportunity to develop crucial work habits.

Children, like adults, are driven by incentives. For many intelligent children, the structure of school does not provide the right incentives. If they can succeed without trying, where is the motivation to work hard? In some cases, the solution might be to remove them from traditional schooling entirely. Homeschooling is an option but it's so much work on parents, and especially as the child gets older, it will get harder and harder to keep ahead of your child's development.Private schools are not always a viable option—they are expensive, and finding one that aligns with a family's values and educational philosophy can be tough or even impossible.

I don't know the answer! If anyone else does, let me know.

Parenting today seems to be undergoing a significant shift, as highlighted by a recent Twitter post. It spoke about how modern parents often trade their own time to save their children’s time—sometimes at seemingly irrational exchanges, like spending 40 minutes to pick a child up from school just to save them 20 minutes of waiting. This kind of prioritization of children's time over their own is different from past generations. There was a time when parents seemed far less invested in whether their children's time was wasted.

This change has brought about both upsides and downsides. kids today have more opportunities to make the most of their time. They might have fewer idle moments, more curated experiences, and a heightened sense that their parents value them deeply. this shift might be contributing to a sense of entitlement. When children constantly receive the message that their time is more important than anyone else's, they may grow to feel that they are the central figures not just in their families, but in any setting they inhabit.

I wonder if this trend is tied to the rise of helicopter parenting. I recently watched kids at a playground in California, with parents trailing and hovering, ready to intervene at the first sign of trouble. In contrast, in Las Vegas, things look more like when I grew up—parents sitting back, letting their children sort things out themselves. The differences in parental involvement seemed to speak volumes about changing philosophies of what good parenting looks like. This might also be tied to politics. California tends to have a more liberal population, whereas in Las Vegas, the population is split between liberal and conservative, and even the liberals tend to be more union-oriented rather than socially liberal.

Are kids today better or worse off because of these shifts? It's complicated. In many ways, they're better—they have more support, more time to explore their interests, and a deeper connection with their parents. I've also noticed that kids today are much kinder than they were when I was growing up. There's less bullying, less casual cruelty. But in other ways, they might be worse off—perhaps they lack resilience, or an understanding of their place in the broader social fabric, because they've always been made to feel like the center of the universe.

And what about the parents? There's certainly a cost to this kind of hyper-involvement. It’s exhausting and takes away from parents' ability to lead their own lives and be individuals. It's a much greater sacrifice than what parenting was in the past. Yet the connection many parents now have with their children seems far deeper than what was typical in past generations.

Ultimately, these are all tradeoffs. Time will tell as the children of this generation grow up, become adults, and either reflect our own parenting efforts or reject them when they become parents themselves.

A lot of my family's long-term planning has centered around how to preserve this strong relationship with our kids, while also giving ourselves time to be ourselves. What do we need to exist around us for that to happen? That's part of why I'm so focused on the idea of urbanism – I want to live in a place that is dense enough to allow my children to grow up knowing how a wide variety of other people live, safe enough to explore the world around them independently, and ideally, equitable enough that they can make their way in that world no matter what path they choose. Finding such a place in the US has so far seemed like a pipe dream.

In reading this article about the damage wrought upon Ghana by the trade in used clothing, I see a larger trend.

As the world becomes richer, places like Ghana are becoming less common. What I mean by that is at some point, there will be no more Ghana's to give all the discarded clothing to.

Richer people in the US and Europe consume clothing at a fast pace, and donate these clothes to charity shops. The charity shops sell 20% of it, and the rest gets baled up and shipped overseas to places like Ghana, the Philippines, etc., where it is sold to locals. Then the remaining 40% or something that is not sold is disposed of, often improperly, because local governments can't actually afford to properly dispose of the waste of much richer societies.

The same thing plays out in recycling, and China deciding to stop playing at the receiving end of this game has thrown a lot of “recycling” efforts into doubt, as it slowly dawns on us that likely none of this stuff was actually getting recycled anyway.

I suppose we can keep going if we build big enough landfills. I am not sure about the economics of landfills, though I do believe that environmentally they aren't too bad. Things like textiles should likely go into landfills quite safely, after all, even moreso than plastics.

But is there a point where we decide as a society that this isn't worth it? I'm not sure. If there is, there has to be a next step.

Actually durable materials? Actual recycling? Moving away from single use plastics and the like? If anything, we're moving towards these things, and the alternatives are often somehow worse, like the case of reusable shopping bags which are often not reused enough times to make their use more environmentally friendly than just using the thin plastic bags in the first place.

I worry that it's more complicated than anyone wants to reckon with, and the simple solutions often actually hurt more than they help.

When I think about that, and consider how, at least in the US, the government has reacted to what are conceptually quite simple problems (transportation, housing, racial equity), I have little hope for our ability to address these more complicated problems with our current government.

I see glimmers of hope in places where there appears to be more competence in government, but this competence also comes with costs. In Europe, competence in addressing human needs comes with economic costs. Maybe they don't matter that much if people are happier, but it is a mixed bag there. In some places, people seem to be happier. In others, it seems they aren't.

In Asia, the competence seems to come with a loss of freedom, like in Singapore, or the exploitation of a neighboring, poorer country (also Singapore, Hong Kong, and other places). In Europe and America, our exploitation of others is more at an arm's length, through trade and the exporting of waste, pollution, and so on. In Asia, exploitation is up close and personal, with domestic helpers and manual laborers from neighboring countries who have second-tier employment rights and no stake in the governance of the country they live in and work within.

I don't have any solutions, just wondering how we progress. Are we stuck at a local maximum, bounded by our own state capacity? It would be a shame if the march of progress was halted by such a simple thing, but the technology of government seems to have stalled quite a while ago.

“The 84-year-old white man accused of shooting Black teen Ralph Yarl in the head for ringing the wrong doorbell “spent considerable time at home in a living room chair, watching conservative news programs at high volume,” one of his relatives told The New York Times…

source

I've been telling everyone who wants to listen about how land use is the source of so many American problems, and I'm once again going to link land use to the rash of killings lately perpetrated by people who have unreasonable fear of someone showing up at their door, or getting close to their car, or pulling into their driveway (three recent incidents of people being shot for no good reason).

Land use determines social cohesion

Suburban and rural populations are less close to their neighbors, just as a geographical fact. They are also farther from their jobs, at least on average, than urban populations.

This means that to get to and from work, they spend more time commuting, and in the US this means sitting in their cars.

More time commuting is less time spent at home, less time available to develop relationships with neighbors, to spend with family. It's less energy available (anyone who has had a long car commute knows how tired you get from it).

What happens when people get home late, already tired? They watch TV. This habit gets ingrained in us during our working careers in America, and can you blame us? Who has energy to go out and hang with the neighbors after 90 minutes of commuting and 8 hours of work?

Compare it to being in a walkable city, and your commute is under 30 minutes each way, and you don't have to drive (so you can listen to an audiobook, read something, listen to music, whatever). Not only are you closer to your neighbors, you have the energy to interact with them on weeknights.

Aging in America is a process of becoming more and more isolated

Unless you pack up and move to Florida or some other dedicated retirement community, people who age in their homes are at unique risk of isolation in America. You are surrounded by people commuting huge distances to work, who have no time or energy to interact with you.

As people age, they get less confident in driving, and eventually lose the ability to drive altogether. Now you are in a place where you can no longer get around by yourself, and are dependent on family or paratransit services to get to important appointments. You are not going out to socialize on a whim very often.

What do you do? You sit inside, and watch TV. Eventually you run out of shows to watch or get bored of them, so you tune into the 24 hour news, because it's always fresh information (seemingly) and it's more exciting.

Sound familiar to the quote at the top of this piece? It's not just old people getting radicalized by Fox News, OAN, and the like, but I'd wager that a very high percentage of older people are getting sucked in by it, because of this dynamic.

There are no easy answers in America

So much of our society is already built around cars. There are no safe, affordable, walkable areas in any city in the US (choose two of those three, basically). There is no transit to get you to a walkable area if you live outside of one.

Changing that is probably the work of several generations, even if people wanted it to happen. The rub? They don't want it. Why don't they want it? Well, the latest culture war battle has been against the 15 minute city. I can only guess that the people who run the Fox News' of the world realized that if people become more urban, their hold on them will decrease. So people have been convinced that living in a place where all your needs are available within 15 minutes of walking or transit, is somehow a bad thing.

The very dynamic that is causing the problem is preventing us from solving the problem, at least in part.

Of course there are many more reasons. The appeal of a big house and car are undeniable. Even people in Europe are getting sucked into the idea. But it's a case of choosing to eat sweets for every meal because they taste good, and ending up with diabetes, but at a societal scale. Even though living closer together would be better for us, we don't want to accept it and figure out how to make it work.