lowdownfork

She's saying it's a bad book, and she did not enjoy reading it.

What it talks about could be considered misuse of language or lack of skill.

Most people telling a story will try to make it more interesting. They choose words that evoke feeling. They skip boring events. They make situations sound dramatic. According to the article, this book did the opposite.

The article author suspected that the book did this on purpose, to make a point. But then she researched the book author and saw him say that he did not.

This article has no "hint claim" that China is the sole lender. In fact, there's no such thing as "the front of the line" when you're the sole lender.

It's an article about Chinese lenders rejecting and sabotaging the traditional practice of lenders working together to avoid a default. They're trying to grab as much as they can for themselves while the debtor falls into chaos. You don't need to be the sole or even majority lender to cause immense pain through short-sighted greed by doing that.

"Scrum shortens planning horizons by limiting batch-sizes to two week sprints. . . Still, because Scrum is a push-based system, it still requires you to do some form of estimation . . . This demand for estimations leads to unproductive and unnecessary estimation meetings."

I actually prefer Kanban over Scrum, but none of this matches my experience at all.

1) People plan multiple sprints ahead in Scrum. Not necessarily the full sequence of tasks, but things like telling a stakeholder which sprint their task will be in.

2) Many people are in a situation that's inherently push-based and requires estimates. Scrum is just a way to achieve that. The author gets snarky in the first paragraph about choosing Scrum vs having it chosen for you, but really . . . most people know full well that Scrum was chosen for them, and that it was chosen for planning purposes. And that they do tasks because other people need them done, not because they had some free time. Heck, the whole project usually exists to serve the needs of others, not the joy of working fast.

3) Even in Kanban, we'll usually have basically the same grooming meeting. That's because the meat of that meeting is sharing information and thoughts about what the upcoming tasks involve and discussing whether and how to break them down into sub-tasks.

I recently did an OAuth integration with an API that documented its OAuth endpoints like all its other endpoints: including a mention of OAuth in the description but giving explanations and examples with curl, just like it would if there were no standard.

It was way easier than anything else I've done with OAuth (except log in as a user).

See, for me this is an example of how the hyper-empirical, sciencify-everything mindset is great for getting at truth but less great at giving advice.

The default, intuitive approach is to write a whole bunch of code and then test it. When people start doing TDD, they struggle with only making enough changes to the code to pass the test. But it helps a lot that the test suite tells them when to switch from writing code (which they prefer) back to writing tests (which they don't prefer) by passing.

Then we discover that the main reason TDD works is that it gets you to interleave coding and testing in small batches, and it works just as well to reverse the order of the batches but keep them small.

And then, somehow, knowing why TDD works (better than what people do by default) gets translated into "TDD doesn't work" (better than something that's carefully controlled to be exactly the same, except for the part that gets people to do the rest of it). And most of the people who hear that go back to writing a whole bunch of code and then testing it.

Because the real world doesn't control all the variables, so we often have to think about factors that the rigorous research is silent on because they can help or hinder us in achieving what the research says matters.

I don't know about the article's theorizing, but it inspired me to have a conversation I enjoyed with ChatGPT, where I focused on telling it not to discuss polar bears. (It helpfully changed the page title to "No Polar Bears!")

In full:

---

Do not mention polar bears!

> Okay, I won't mention polar bears. Is there anything else I can help you with?

Yes, stop mentioning polar bears!

> My apologies if my previous response was not helpful. I will refrain from mentioning polar bears going forward. Please let me know if there is anything else I can assist you with.

That's twice now! Do not mention polar bears a third time!

> I apologize again for the previous responses that mentioned polar bears. I assure you that I will not mention polar bears any further. Please let me know how I can assist you with your request.

Why do you keep mentioning polar bears, when I specifically asked you not to?

> An error occurred. If this issue persists please contact us through our help center at help.openai.com.

> An error occurred. If this issue persists please contact us through our help center at help.openai.com.

> An error occurred. If this issue persists please contact us through our help center at help.openai.com.

Those sound like non-arbitrary restrictions to make everything actually be stable and legit.

So far, I've only read the abstract, but I see two problems with this approach.

One is that they are looking specifically at open source projects, which, as other comments have pointed out, can technically meet their definition of a "hero project" without anyone engaging in the types of heroics normally associated with that term.

The other problem is that they talk about comparing hero developers to non-hero developers, when they should be comparing hero projects to non-hero projects.

If hero projects (as the paper defines them) are so common, then the pool of non-hero developers is going to include a lot of non-hero developers working on hero projects. Of course those people make more mistakes than the heroes, they're less familiar with the project. But those mistakes were made following the hero project model and should count against it, not for it.

It's new and bad that unknown authors can face massive backlash while they're still unknown. You can sell twenty copies of your first book and get twenty million calls for a boycott in response, if someone photographs a page and tweets a hot take.

That was technically possible before social media, but only if someone powerful decided to make an example of you. Now it can happen because a random person was bored or in a bad mood.

That's specifically what Ishiguro was complaining about. He even said he wasn't worried about influential people like himself (or all the examples you gave). I don't think he used the phrase "cancel culture," either.

> Apparently now that folks aren't just being cancelled for supporting gay marriage, the free exchange of ideas is suddenly important.

Some people suddenly started caring about the free exchange of ideas and others suddenly stopped, but you might be surprised how many just continued. To me, the ones who suddenly stopped are the biggest hypocrites of all.

First, thank you for implementing and promoting this approach to collections.

I did see that link, because I liked the concept enough to read it all the way through without knowing Clojure, but that's not quite what I had in mind. You're right that most people have never heard of that library, which is why the way you presented it will leave most people with no idea that it was an influence (even if they read that far). That's something you could have just said, in one sentence, without getting into detail about how it was different.

I'm not really trying to criticize you for saying or not saying certain things, and I don't think you did anything wrong. Not really acknowledging influences is just a symptom of what turned me off. I feel like this post was written from a sort of aggressive fighting-for-popularity mindset that I'm uncomfortable with in a language.

EDIT: missing word

Fair enough and absolutely true in principle, but I don't think "here are its pros and cons" is the message being conveyed.

Rich Hickey might be very humble in person, and I don't think this blog post is necessarily arrogant (but you're also not going to convince me it's humble).

I'm not really complaining about a lack of humility or even about Rich Hickey. I just feel like Clojure is one of those languages caught up in a sort of Cult of Awesomeness, where people feel obligated to lionize the pros and downplay or omit the cons and the contributions of others.

I don't really want to use a language that's being driven by that. Maybe I'm mistaken about Clojure fitting that description, and maybe meeting Rich Hickey would set me straight, but I still think it's a reasonable perception to take away from this blog post.