skybrian

Yes, a conversation can be the plan. It helps if you ask it what the commits will be and then tell it to use subagents to implement them.

Also, since sometimes an AI can be a busy beaver, I added instructions to not edit any checked-in files if the prompt contains a question.

Foster City has a pretty hefty levee [1]. Palo Alto is building a "horizontal levee" [2]. Looks like Redwood Shores will be raising theirs [3].

This work has to be done for good reason, but looks like they're on it?

[1] https://fostercitylevee.org/ [2] https://www.sfchronicle.com/climate/article/palo-alto-sea-le... [3] https://www.smdailyjournal.com/news/local/new-200m-levee-upg...

Looks like this is complicated and the short answer is "it depends":

https://chatgpt.com/share/6ab5ca51-3e0c-83e8-a232-892d3e4ef9...

If mortgage expenses go down and property tax expenses go up, it's basically a wash.

But for that to happen, land values need to go down. Landlords need to bid less.

So what happens then? High enough property taxes could in theory result in a situation like Detroit where the land value drops so low that properties are abandoned, with no buyers. But that seems unlikely in California?

At less of an extreme, there are still buyers, but they offer less money so they can still make a profit. So, the property tax basically comes out of land values. The current owners lose money on the property. It's the opposite of the windfall profits that California property owners have gotten from rising land values, taken out of whoever owns the land now.

For the next owner, their mortgage expense is lower, their property tax is higher, and maybe rents and profit margins stay about the same.

Notice that if the demand is there, falling land values doesn't result in lower rents. If your complaint is that the rent is too damn high, higher property taxes won't fix it. Only more housing does that.

I'm a bit skeptical that it would really work out that way. In California, we can have the odd situation where the current owner pays low property taxes, the new owner will pay higher property taxes, and yet property prices get bid up, and whoever buys it has to pay both more property tax and a higher mortgage. But they can still afford it, because there are a lot of rich people out there.

I think the idea is that if the market demand is such that it allows them to raise rents, they'd already have done it, whether or not expenses justify it.

There are people who don’t save money at all and people who save a lot more than average, which is a whole lot easier with a high income. With the right mindset, it’s not much of a hardship.

This sounds like the toupee fallacy.

I wonder if any movie special effects that you notice will be considered AI?

Also true of a land mine, but that’s not very reassuring.

Motivation or not, I find a coding agent can be quite the busy beaver. Ask a question and it goes off and does it. I certainly don’t need to motivate them. I had to put a line in AGENTS.md to make no changes when there’s a question in the prompt. It doesn’t always work.

Seems like motivation is irrelevant? They don’t need it.

Why not both? Depending on what you make, it’s often possible to enjoy life and also spend less than you earn. You are enjoying life like someone with a lower salary would.

Similarly, you shouldn't say "I flew to San Francisco" because it gives you bird characteristics. "I rode in an airplane that flew to San Francisco" is clearer.

:-)

I don't know how "sandbox" became "prison," but exe.dev does this sort of thing pretty well, and a web UI can be as good or better than a terminal interface.

There are some projects I'd consider to be useless, but it doesn't seem very likely that data centers will be useless. Maybe not used for their original purpose, though?

Extinction due to building too many data centers? How would that even work?

It’s being jammed into products where it’s not wanted. I use AI every day with good results, but I do not want it in my browser, my OS, my text editor, or AI summaries in my search engine. I want it in a separate web app where I can use it or not.

So am I pro- or anti- AI? Both. It depends what it is.

It can be bad for some people (many stories in the news about this) while still being good for other people. Hard to say overall or in the long run.

Does it still matter now that we have Linux VMs and Docker files? Seems like OS on the actual hardware could be any Linux or even non-Linux.

This is assuming all or nothing. More likely they will co-exist.

There are good reasons to have choices. Driverless cars will make more sense if you have a lot of luggage or other cargo to schlep. Elderly people might find it easier. There will be routes that are awkward by bus.

Also driverless vans might make sense on some routes.

It will help if incentives encourage the use of whatever is more efficient.

It makes a lot more sense for Bart. You can go places that don’t even have Waymo service.

Arresting people on the spot is punishment too, more arbitrary and less effective. It just seems worse?

Also, the experience of riding Bart seems to have improved quite a bit since they installed better turnstiles, and that likely will affect ridership numbers.

I think of food delivery in urban areas as a good test case for “are people really going to lose their jobs to robots?” I think it’s gonna be a while? Unless it’s the customer doing some of the work by going down to the street to take the food out of the Waymo.

Delivering bombs is much easier, unfortunately.

It's mostly fast enough for most apps and that definitely helps. It's not as consistently fast as some languages that don't rely on an JIT. That matters more for tooling than your average website.

If there were companies that never got hacked, how would you notice?

That’s true of everything you build. The cost of land has to be taken into account, but land is much cheaper in some areas than others.

Rather than focusing on OpenAI in particular, let's just say that there are many smart people at other AI labs and if it seems like it will be popular, this technique will probably be copied. What would prevent them from adding another API?

Hopefully there will be some decent benchmarks and gateways for switching between providers easily.

It's good to think about where you're going, but you also have to keep track of where you are.

(Also, getting people to think about the future rather than the present is a classic con. Looking at an empty field: "can't you just see the potential here?")

Yes, it's certainly possible to generate code faster than you can clean it up. That's a choice. (Often called technical debt.)

This is a bit too future-oriented. Let's not mix up current capabilities and speculation about future capabilities. For the time being, collaboration works well. What the future brings is uncertain.

You can still read the code, ask the AI questions about it, and ask it to fix things. Coding agents are a power tool for cleaning up codebases, but you have to ask for the right cleanups, which means figuring out what it is based on your understanding. (You can also ask the AI to suggest ideas.)

This takes time away from implementing new features, but that’s true of all code health maintenance.

src/md doesn’t seem all that different from docs. Maybe it changes how people search the filesystem, though?

If you split code up into multiple packages, moving the docs closer to the code might make sense. The docs for package foo could be in packages/foo/docs.