5
points
drcxd
Joined 19 karma
A video game programmer, interested in video games, reading, and music...
- drcxdStrictly speaking, Lua is not global by default. All free names, that is, all names unqualified with `local`, is actually indexed from a table `_ENV`, which is set to `_G`, the global environment. So, all free names are effectively global by default, but you can change this behavior by put this line at the top of your file `local _G = _G; _ENV = {};`. This way, all free names are indexed from this new table, and all access to the global names must explicitly be accessed through `_G`, which is a local variable now. However, I have never seen such practice. Maybe it is just too complicated to accept that all free names are global variables and you have to explicitly make it local.
- Obviously, since the training material for such esoteric languages is scarce. (That's why they are esoteric!) So by definition, LLM will never be good at esoteric languages.
- I have been watching for Typst for more than a year but there are still things Typst can not do as easily as LaTeX, see https://qwinsi.github.io/tex2typst-webapp/impl-in-typst.html for examples. So, I do not agree with the statement that Typst can fully replace LaTeX, at least, for now.
Other than the product itself, there are ecosystem issues as well. LaTeX has mature support in editors such as Emacs. However, support for Typst in Emacs is still in development. Thus, for now, I will keep using LaTeX, but I would keep Typst as an option.
- > I believe the AI agentic coders will threat tech giants more than it - collectively - threats software engineers.
Currently, I don't think so. Coding agents' performance generally depends on the quality of the model behind them. Running a powerful model is assets-dependent. Not everyone has the hardware and power to support Sonnet 4.5 or Gemini 3 even if they are open-source. So, before the top notch models can be deployed on personal computing devices, I would not say coding agents will threat any organization.
- Yeah, code is data, data is code. Every Lisp programmer knows that.
- True. Arch Wiki is one of the best documentation system I have ever seen, which is also why I always choose Arch-derived OSes.
- The moment I saw this post, the idea of submitting itself to itself came to me. Really amusing.
- Glad to see I am not the only HN users that work in such companies.
- Remind me the another recent post: You should write an agent https://www.hackerneue.com/item?id=45840088
- > Me: It sounds like you’ve got mixed emotions at the moment. On the one hand, you’re happy that your boss says you’re doing a good job. But you’re questioning that, given the problems you’re having with Legal. Did I get that right?
No offense. However, this response from the first example feels robotic to me. It feels like I am talking with some kind of artificial intelligence. I guess we have to make it sounds more natural. In fact, the following examples feel more smooth to me.
- Also tried that, but I did not noticed the memory leak problem, since I only played about 1 hour. There are other minor issues about using Linux, for example, my input method does not work in the Steam chat window, but works everywhere else. Anyway, Linux is much more cleaner than Windows and it is a overall better development environment, I prefer it over Windows now.
- Hello, have you ever tried using the coding agents?
For example, you can pull the library code to your working environment and install the coding agent there as well. Then you can ask them to read specific files, or even all files in the library. I believe (according to my personal experience) this would significantly decrease the possibility of hallucinating.
- Agreed. I also have to check if it has implemented the idea correctly.
If my workflow is;
1. Write documentation so that the problem and even the solution to the problem is well explained. 2. Instruct coding agents to work as the document described. 3. Check its if its implementation is correct, and improve its implementation if necessary.
I feel the experience is not as good as me implementing the solution myself, and it may even take more time.
- Thanks for you opinion. I agree with your opinion that current LLMs are less helpful to senior/experienced developers. Of course LLMs can't solve complicated, advanced problems, otherwise we would see great advance in science and technology now.
However, there are a lot of trivial work in software development. For example, the behavior of a button, or editable text. Same to any kind of art, most developers in the industry are doing trivial or ordinary work, and few are solving challenging problems. What I mean is that those who do trivial work will be culled, or liberated, from doing that as a job, while the elite could remain there to solve unique, challenging problems.
Recently I have been working with coding agent to fix bugs and implement new features. I implemented my solution first and let coding agent come up with its own solution. Most of the time, the coding agent came up a better solution than mine. Most of the time, its solution was not worse than mine, and I would keep most of its code and only do some minor improvement. Most probably, I am not an experienced/advanced developer, since I seldom deal with advanced math/algorithms/architecture in my day-to-day work. Thus, it would be natural that we have different feeling to the same thing.
I am interested in Dijkstra's idea about natural language programming you mentioned, is that EWD667?
https://www.cs.utexas.edu/~EWD/transcriptions/EWD06xx/EWD667...
- Do you really believe that if you miss the "Read Clean Code" or "Read Effective Typescript" part, then the output would be significantly different?
No offense, but I feel this kind of talking is ridiculous. If it is a better practice, then it should be done without explicitly telling so. You do not tell them "Do not get things wrong," right? If it is a matter of choice over design patterns, for example, use functional programming or object oriented programming paradigm, then it should be said more clearly as what I have done.
Now, if it is neither something that is definitely a better practice nor something you can state clearly with a known, well-defined word, how can you make sure what you have said really make a difference if you have not said it?
- > Software engineers are the translators.
True, recently I started feeling that part of what I had been doing is simply translating natural language to programming languages. Though coding also involves things such as algorithm and data structures, context and background knowledge, but these can all be done in natural language. Once the natural language description is given, what remains is only translation. LLMs have good knowledge of almost anything, though they are currently weak on inference or derivation, but this already makes them good on the two end of software engineering -- context knowledge and translation.
I understand those people who hate LLMs for coding, I partly share the feeling, because I enjoy typing on a keyboard, editing part of the code, reading the characters, I am an Emacs user. If LLMs can do the work, even if just save the typing and editing part, some of the fun has been eliminated for me.
Think about chess and Go, though AI can easily beats human now, people are still playing it. For programming, if one day AI can do 80% of the programming work, I guess only few of programmers today can keep doing it as a job. Just like few people can play chess and Go as their job.
- Yeah, can't agree more. LLMs are good at getting you started, but you still have to read the code, learn something, make it your own, so that when LLMs start to suck, you know how to solve the problem on your own.