drcxd

Which means, they have to value human lives higher than LLM servers.

Not really. Jev is NOT a HUMAN.

Interesting, recently I am working on my own clone of Pac-Man. LLM implementations lose lots of details. They are not 1:1 replication of the original game. For example, the behavior of the ghost is not the same as the original. If I have not implemented the game myself, I can not tell the differences. What LLM produced look like the original game, but they are not.

It feels like understanding is no longer required to produce code, as long as the program can pass the tests. Also, most software rarely causes severe real world damage, so it simply requires less guarantee and quality than other engineering such as buildings, bridges, etc.. With LLMs, code is just like cars, it carries you to your destination, you do not have to understand how it works.

You can't call people lazy because they use LLMs, just like you can't call people lazy because they travel by train/plane/cars instead of their own feet.

Where is the real hacker community then?

Yeah, it's just how you see programming in your perspective.

It's like lifting weight. Obviously, machines lift weight much better than human for a long time. But people still trains for strength or aesthetics. Even if machine can lift much larger weight and more efficiently, some people still care about how strong they are.

A machine can lift much more weight obviously is not the excuse for them to stop training.

Programming is just the weight lifting for your brain/mind. Even if LLMs can solve all coding problems perfectly, there will be people who still want to program all by hands, for training their mind, or simply enjoying the process. And there will be people care about how good you are at solving a problem with programming.

LLMs being able to code does not mean you no longer need the ability to code.

Cars do not mean you no longer need the ability to walk.

Me literally searching for emacs in the webpage.

Nobody notices that all the messages are labeled "5:42 pm"? From the proposition of the idea to the the review of the PR. This of course is impossible. I mean, even AI bots can understand and implement the features that fast, it is impossible for your human colleagues to notice your message and respond in the same minute. So, this image is also generated by AI?

Assume you build a machine that can simulate some system 1:1. Then it means the machine is exactly the same as the system, and the cost of running it will no less than the system itself.

If you want to reduce the cost but still get something useful, you have to make some abstraction, and we all know that any abstraction is leaky.

A leet-code style automated assignment is like a test. We all did tests in school so I guess most people do not feel there is anything wrong about that.

However, an interview, which should be conducted by human, but instead by something AI pretends to be human, would make most of the current human beings feel disgusted, naturally.

Is there any formal proof that an AI conducted interview yields more than a pencil & paper test? Or is there any scientific research about that? I doubt there would be any in the near future. Then using such AI conducted interviews is simply a belief.

You miss read. The parent thread said: > the women has am easier time not to commit and just sleep around That's for women. The second time they mentioned sleep round: > Dating apps are available, statistically women all try to get into a relationship with the same 1% of men - who sleep around and cause toxicity all around. They mean the 1% of men are the ones who sleep around. Also, I think it is better to interpret "sleep around" as the state of having non-committed sex relationship with non-marital partner. It is a description of a fact rather than an accusation. Though the words may sound harsh.

In my opinion, reproduction is based on the idea "borrowing against the future", or Ponzi Scheme, because reproduction is based on the idea that "we would have a better future", but in fact, we will not.

Yeah, and if there really is any boilerplate thing, can't we programmers come up with a more deterministic solution, like a framework? I don't know.

This reminds me of the video game crash of 1983: https://en.wikipedia.org/wiki/Video_game_crash_of_1983

Because video games of poor quality are too many, consumers simply refuse to spend time identifying the high-quality ones from the enormous poor-quality ones.

I wonder if the software industry would experience the similar thing?

I like your idea of finding the pattern of those "embarrassing LLM questions". However, I do not understand your example. What is a random program? Is it a program that compiles/executes without error but can literally do anything? Also, how do you translate a program to plain English?

news.ycombinator.com/item?id=46670279

Recently there was this post which is largely generated by Claude Code. Read it.

But the dashboard is not important at all, because everyone can have the same dashboard the same way you have it. It's like you are generating a static website using Hugo and apply a theme provided on it. The end product you get is something built by a streamline. No taste, no soul, no effort. (Of course, the effort is behind the design and produce of the streamline, but not the product produced by the streamline.)

Now, if you want to use the dashboard do something else really brilliant, it is good enough for means. Just make sure the dashboard is not the end.

Strictly 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://news.ycombinator.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.