I use a similar system at work.

Off the top of my head, I have used it to put links together — for example, a Stack Overflow description of some bug, the official documentation, and maybe copying in the exception or the error message.

Then I've sometimes done the same thing when I'm doing ops on a broken system.

Other times it's copying in a specific query or a link to a query in Application Insights.

Other times it's the ticket I was working on, a comment from a coworker, and maybe a few references to either tickets or files. Very rarely is this professional or looks nice. It's just that I need one place where I can put multiple things that fit together.

I find that retrieval does drop off very quickly. But that's just to say most of the value is front loaded. And we should not underestimate the value of being able to answer 'da fuck was I doing yesterday'. Context switching is expensive. But in many ways it is also unavoidable. If you context dump at the end of a workday, it's that much easier to return to it later.

The other thing I do is because the note system I use can I can drop in Hashtags. Yeah, I know. Not exactly HN friendly. What that means is I can find all the times I ran into the same issue, sort of weaving a meta thread through my work. It's really hard to explain, but it's one way of treating notes as not just segments of text.

>My spouse is a lab scientist, and I've seen her meticulous notebooks. She was telling me just last week that one of her experiments produced a puzzling result. The next day she said: "I figured it out from my notebook. I skipped a step that was in the procedure."

This puzzles me. If you are skipping a step in the procedure, aren't you also possibly going to skip writing a step down? And if you're not sure you wrote the exact right steps down, how are you going to use the notebook for that purpose?

What if you have to do several steps rather quickly? Say adding a particular chemical, then waiting for ten seconds and adding, another chemical? Do you have time to write it down?

> If you are skipping a step in the procedure, aren't you also possibly going to skip writing a step down?

Exactly, so when she reviewed the notebook, she caught the error.

Even if she made a slip in the notebook, merely reviewing it helps jog the memory to revisit and replay what she did in the lab. It's the power of touchstones.

> What if you have to do several steps rather quickly? Say adding a particular chemical, then waiting for ten seconds and adding, another chemical? Do you have time to write it down?

The notebook doesn't always have to operate as a log. It can also operate as a plan of action.

I think you're missing one element. It works. The culture in Germany in 1600 compared with the culture in Germany in 2026 is very, very different, even though the geography hasn't changed. That's because in the modern world nearly none of the culture of the old Germany works.

This is not unique to Germany, of course. We long ago gave up on the four humours theory. We long ago gave up on burning women who wear pants. We long ago gave up of many things that used to be European culture.

The culture of queuing in Japan works because you are looked down upon if you don't participate and because it is better than the random stuff we do in the West. However, it would probably disappear pretty soon if it wasn't also a good solution.

While I tend to agree with your general example, there are lots of products that people don't talk about because they are icky, personal, or embarrassing but also really useful. Period cups fall into this category. Ting or whatever needs to advertise because nobody talks with their friends about phone subs.

Facebook knows I graduated with a degree in comp. science and when (since I told them). They could therefore infer that I am into nerdy things - but I get bottom of the barrel ads.

Part of the problem as far as I can see is that there is no way to mark an add as insultingly matched.

There is no shortage of money to build housing. There is an abundance of regulatory burdens in places that are desirable to live in.

Its not due to a lack of money that housing in SF is extremely expensive.

SF is not the only place where housing is expensive. There are plenty of cities where they could build more housing and they don't because it isn't profitable or because they don't have the workers to build more, not because the government is telling them they can't.

It is expensive in those other places for similar reasons as SF -- the government either tells them they can't (through zoning), or makes it very expensive (through regulation, like IZ / "affordable" housing), or limit profitability (rent control), or some combination of the above. All of these reduce the supply of new housing.

Generally the cities where housing is expensive are exactly the ones where the government is telling people they can't build (or making it very expensive to get approval). Do you have a specific example of a city such as you claim?

Which cities, for example?

Awesome. Any chance we will see a phone app?

I know coding on a phone sounds stupid, but with an agent it’s mostly approvals and small comments.

The ChatGPT app on iOS has a Codex page, though it only seems to be for the "cloud" version.

They put it into the Azure portal, and I tried to get it to answer me what the open resource cost us in storage. It appeared retarded at first, but then I realized it didn't have access to know what I had opened or anything.

Until MS makes sure their models get the necessary context, I don't even care to click on them.

I think a good workflow is to use the llm as a minimum to fix typo and grammar issues.

From there you can also go from first draft to feedback.

Openapi can do that too. But the real benefit is that it forces a simplification of the interface. XML has too many outs for architectural astronauts. JSON has close to none.