Hacker Newsnew | past | comments | ask | show | jobs | submit | HackerQED's commentslogin

Yeah, the naming of `llms.txt` feels awkward. But I know a guy gaining 10K visits within a month by using it correctly.

About the naming and the standard (it's still a proposal), see https://llmstxt.org/

There are also many discussions about llms.txt in HN ;)


great article. Read it 1 year ago and still very informative.


A fun idea, but it should not be put in the ordinary flow. It will hurt users.

`man -abba` would be nicer, as the author said in the original post.


The first answer explains that it was only supposed to trigger on error cases (no page specified) but due to an oversight also triggered if you specified a man page by the --path flag (rather than just the page name)


  $ man --abba --format=json
  ["gimme", "gimme", "gimme"]



RIP. He is an old man with wisdom and a sense of humor.


That's right, straight to the point.


Cool, imagine after a collapse of civilization, last survivors dig out this, as the cornerstone to rebuild the old-time industry.

This card has such a sci-fi taste.


> now it's 2024 and we've screwed it all up.

Moved to tears. A strong sense of 'How Time Flies'.


Great, and the more you know about software engineering, the better it would perform.

IMO, the 1st law of SE is about creating a bounded context, to make any junior can work like a senior.

And Cursor is a really hardworking and smart junior.


It's also great with TDD if you have decent coverage and want to maintain decent coverage.

One thing I dislike about TDD is I sometimes think better in code than use cases. And stuff like mocks etc take far longer to write than a 5 line fix. Say, I have a repo where it takes variable from source A when X happens, and source B when Y happens.

Now I can do reverse TDD. I write the code first. I highlight my code and tell Cursor to write the tests. I tag all the classes and models and other things that I want Cursor to mock. It writes the test, the tests pass, green. Then I stage the code that I wrote, and those tests should fail, red. It also finds all the dumb things I missed out on like imports.

So there, I have a pair programmer that writes the 300 lines of tests while I write the 5 lines of functional code, no worries about hallucinations and all.


>And stuff like mocks etc take far longer to write than a 5 line fix

If you test from the outside in and build up a library of functional and realistic fakes then over time then this gets quicker and easier.

Ideally I think people shouldnt use mock objects at all, ever - only fakes of varying realism at the edge of the project, populated with realistic data.

One reason for doing TDD is that it compels you to match a realistic test with a realistic scenario. I tend to find people lose that when they do test after, and they instead lock the test in to the current behavior of the code instead. This is not just tedious work, it's also harmful.


Really this. It’s been great for me to dive into an unknown area with a new library from scratch.

Explanations of code work relatively well for smaller chunks of code.

When files get larger, I get more of a miss rate/bad suggestions unless I start tightening the scope.


Cursor team's attempt of Structured Prompt Design, using a React-like style.

They even wrote an article about it: https://www.cursor.com/blog/prompt-design

The library hasn’t been updated for six or seven months.

- Maybe they see it as valuable and took it internal

- Maybe it's like LangChain, a dead end of over-optimization.

I believe the former is more likely.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: