tobyjsullivan

The Nature of Economies by Jane Jacobs

People complain about how it's written, but it's nevertheless an interesting exploration of the parallels between natural ecosystems and human economies. As someone with no particular interest or background in economics (and who hasn't read anything else by Jane Jacobs), I find it a fascinating and easy read.

The article has been edited significantly - effectively rewritten - since I commented (see archive linked from a comment). So, yes, the new version may provide more details and tell a very different story.

The technical details are in the article. "material that was not intended for public access" was available on "the public-facing Medicare Statistics Reporting Service portal". In other words, they put sensitive data in the open, and somebody looked. It seems obnoxiously apparent that everything else about the framing ("OpenAI agent", "breach") is driven by politics.

The 90's was people worried they'd be treated as nothing more than a number. 2020's is people wishing they could be known only by a number (an opaque identifier).

It sounds like you’re defining design as UI/UX design. I think most people include (prioritize, even) things like system architecture, performance bounds, etc.

ISOCP, maybe?

Edit: close, but not quite

I saw a good mental model for this a while ago. Unfortunately I have no idea where.

Three kinds of disability:

1. Permanent (eg, blind)

2. Temporary (eg, pregnant/new parent, recoverable injury)

3. Contextual (eg, holding something with one hand, loud environment)

When people think about accessibility, they often think about 1. But the long-tails for 2 and 3 are huge, and ultimately affect everyone at some point.

I wonder if there’s a version of Maslow’s hierarchy that applies to countries/societies.

You might be reading this through your own filter. It's an overloaded term right now but I took the parent to be referring to actual violent radicalization which is a real online threat: https://rcmp.ca/en/corporate-information/publications-and-ma...

(Forgive the link source - I can see in hindsight how that might not be perceived as the most objective source - but there are many other sources for those who care to look.)

No idea why this comment is getting downvoted so hard. This was exactly what I thought of too, and it provides a concrete answer to the question.

There’s valid concern with these types of laws and scope creep. But there’s also precedent which shows they can work and be applied reasonably.

Apologies, I forgot to use the more general term.

FOSS projects didn’t always have a standard process for Fagan inspections.

https://en.wikipedia.org/wiki/Fagan_inspection

Further to this, the quality problem is affecting the entire industry, not just FOSS. Anyone working on a large enough team has already seen some contributors pushing slop.

And while banning AI outright is certainly an option at a private company, it also feels like throwing out the baby with the bath water. So we’re all searching for a solution together, I think.

There was a time (decades ago) when projects didn’t need to use pull requests. As the pool of contributors grew, new tools were discovered and applied and made FOSS (and private dev) a better experience overall. This feels like a similar situation.

Scanning a few. Some are definitely written by AI but most seem genuinely human (or at least, not claude).

Anecdata: I read five and only found one was AI. Your sampling may vary.

Isn’t this a form of what he labels the “human coefficient”?

Some businesses prefer tools built by other businesses for some tasks. The author advocates pretty plainly to identify and target those opportunities if that’s your strength.

I think his point is to recognize that’s moving toward a niche rather than the norm (on the spectrum of all software to be built).

This seems like the crux of the problem and I suspect this is more of a problem with popular frameworks like Next.js, rather than a general skills issue.

A human isn’t going to read the docs when implementing something they think they already know. Why would an agent?

We go to the docs when we’re stuck or something doesn’t work how we expect, but rarely before.

The question is, should LLMs be trained to behave differently? Maybe?

One way I work around this is instructing agents to always provide external references (eg links to documentation) when crafting implementation plans. That sort of forces to agent to go find supporting docs.

Sounds a bit like man pages. I think you’re onto something.

Skills allow progressive disclosure of information. The theory is an agent will load the skill when it needs access to the specific information.

Skills are listed in the system prompt so an agent should, in theory, know which are available and when to use them.

The author is claiming the agent never loads the skill unless explicitly instructed to.

This somewhat matches my experience, though my agents do load skills at least some of the time. Just not nearly as often as I’d want.

It’s moving fast. Just today I noticed Claude Code now ends plans with a reference to the entire prior conversation (as a .jsonl file on disk) with instructions to check that for more details.

Not sure how well it’s working though (my agents haven’t used it yet)

I believe they’re talking about Claude Code’s built-in agents feature which works fine with a Max subscription.

https://code.claude.com/docs/en/sub-agents

Are you talking about the same thing or something else like having Claude start new shell sessions?

Someone said it best after one of those AWS outages from a fat-fingered config change:

> Automation doesn't just allow you to create/fix things faster. It also allows you to break things faster.

https://news.ycombinator.com/item?id=13775966

Edit: found the original comment from NikolaeVarius

I do like the idea of crowd-sourced collections of resources like skills.

It might be more useful if it was an index of skills managed in GitHub. Sort of like GitHub actions which can be browsed in the marketplace[1] but are ultimately just normal git repos.

[1] https://github.com/marketplace?type=actions

It’s telling that Russia stands out in this list. “One of these is not like the others”

> Paying more for programmers or parking machine processors would be a waste of money.

The rise of parking apps on mobile adds an interesting angle to this.

No doubt, many of us favour apps because the UX is so much better. Not quite sure if that affects the bottom line short-term, but long-term I’m sure it will.

I’ve wondered about this more generally (ie, simply prompting in different languages).

For example, if I ask for a pasta recipe in Italian, will I get a more authentic recipe than in English?

I’m curious if anyone has done much experimenting with this concept.

Edit: I looked up Sapir-Whorf after writing. That’s not exactly where my theory started. I’m thinking more about vector embedding. I.e., the same content in different languages will end up with slightly different positions in vector space. How significantly might that influence the generated response?

I think it’s more for Python libraries that depend on JavaScript.

Lots of packages rely on other languages and runtimes. For example, tabula-py[1] depends on Java.

So if my-package requires a JS runtime, it can add this deno package as its own dependency.

The benefit is consumers only need to specify my-package as a dependency, and the deno runtime will be fetched for free as a transient dependency. This avoids every consumer needing to manage their own JavaScript runtime/environment.

https://pypi.org/project/tabula-py/

Over my 35 years of computer use, most hardware failures (very, very rare) happen during a reboot or power-on. And most of my reboots happen when installing updates. It actually seems like a very high probability in my limited experience.

Of course, it’s possible that the windows update was a factor, when combined with other conditions.

He also seems to talk to a lot of people, and he has access to pretty much anyone given his stature. Imagine being passionate about business and then being able to spend every day talking to people about their businesses and their thoughts on business. I'm surprised he retired at all!

Always worth remembering that PDFs are basically a graphic design format/editor from the 70s. It was never intended for securely redacting documents and while it can be done, that’s not the default behaviour.

No surprise non-experts muck it up and I don’t see that changing until they move to special-purpose tools.

Honestly, I’d still be surprised to learn feathers in America are produced from American poultry. Far more likely the local ones get burned and everything for sale is shipped across the ocean because cheaper.

> agree with authors, every game older than 10 years, and that is not in active development, should be made open source so that community

Note that GTA V is now 12 years old and still sells ~20M copies per year. So that’s going to be a tough sell in some cases.

You could argue it’s still actively developed, particularly due to online, so fair enough.

But that’s also sort of true for Vice City. They’ve released mobile version (playable on Netflix) over the past few years at least.

Nevertheless, I’d be thrilled if that was a standard practice.