Live data from Hacker News

Viewing profile — nadam

nadam

HN member
Joined
Mon, Sep 29, 2008, 3:51 PM UTC
HN karma
1,849
Public activity
481 items

About nadam

Feel free to contact me at: nadam60 at gmail

Recent public activity

  1. comment
    Comment #48918293

    Does anyone know why these Claudisms exist? Are these kind of expressions a result of some kind of 'evolution', so they are more effective in chain-of-thought reasoning that other …

  2. comment
    Comment #46539068

    You put the "agent" word into apostrophes as if I use it as a marketing buzzword. No. An agent is an LLM in a loop with memory usage, with file system access, etc, which is usually…

  3. comment
    Comment #46539007

    Maybe. But I am working with these agents and I see the sophisticated patterns using LLMs, using ground truth data and human experts working together. It could be much more effecti…

  4. comment
    Comment #46538957

    I am amazed at the false dichotomy (ChatGPT vs. Doctors) discussed in the comments. Let's look at it from the perspective of how a complex software is developed with a team of soft…

  5. comment
    Comment #45701893

    I find it amusing how people take this 'leveling game' at big companies so seriously. The title they get at these companies become their identity. They live by the rules the compan…

  6. comment
    Comment #43173322

    I was just thinking about what AI assisted coding brings to the design discussion, especially as AI become more and more powerful and we rely on it more and more. You still want to…

  7. comment
    Comment #43114089

    What I am starting to internalize nowadays is that working faster is useful, but what can really change one's life is learning faster.

  8. comment
    Comment #42578452

    Location: Budapest, Hungary Remote: Yes Willing to relocate: No Technologies: I have the most experience in C++. But there are several others, like, Java, Typescript, Angular, etc.…

  9. comment
    Comment #42567043

    Hmm, I think 'fail fast' and 'embrace the grind' are popular and somewhat contradictory advices. Which is better? I think 'fail fast' is (or was?) a bit overhyped so I tend to err …

  10. comment
    Comment #42439372

    "But when you have to scale the work, then the code has to be easy to read, easy to extend, easy to test, have extensive test coverage, have proper dependency injection / be easy t…

  11. comment
    Comment #42407448

    "When every supermarket aisle looks like a sea of sameness, when every category abides by the same conventions, when every industry has converged on its own singular style, bold br…

  12. comment
    Comment #42039847

    An example is the material editor. When dragging a value of a property of a node (like color) you see it immediately in the editor. You apply a material on an object, (regular obje…

  13. comment
    Comment #42039657

    Re-watching Bret Victor's "Inventing on Principle" was an interesting experience today. At the time of recording (2012) his talk was magical and ahead of its time. Today his princi…

  14. comment
    Comment #41785573

    "compare this with enterprise software, which is orders of magnitude more complex than video games in terms of business logic" Maybe this was true 20 years ago, but I do not think …

  15. comment
    Comment #41531200

    His system prompt is too specific. It worked for me with GPT 4o using this prompt: ---- System prompt: Please note that words coming to you are tokenized, so when you get a task th…

  16. comment
    Comment #40728877

    Or alternatively: 1. Programming in very concrete/practical terms because you do not know how to think in precise and abstract terms (do not know math) 2. Thinking more precisely a…

  17. comment
    Comment #40715611

    Amazing work, prompt engineering at its finest. One future direction for Arc AGI could be to use not Python, but a much more concise programming language that is more suited for br…

  18. comment
    Comment #40656939

    I love this, this is super interesting, but my intuition based on looking at a dozen examples is that the problem is hard, but easy enough that if this problem becomes popular, nea…

  19. comment
    Comment #40586337

    > 'The breaking tech news this year has been the pervasive spread of "AI" (or rather, statistical modeling based on hidden layer neural networks) into everything' Calling current g…

  20. comment
    Comment #40510380

    I think it is important to discuss the notion of accidental complexity and essential complexity here. If your organization's strength is that you have world class engineering essen…

  21. comment
    Comment #40458071

    It is too early to tell for my current project. I know that it is very hard to create a successful game. Certain genres are more crowded than others though. Creating a successful 2…

  22. comment
    Comment #40456720

    It is not just about the financials. It can be a very lonely activity to create something that other people do not care about, or just very very few people care about. (As it is de…

  23. comment
    Comment #40456600

    You are right: it could still work as something I enjoy. It is just that I am in a state of my life where I do not want to put too much time into such an activity: I have a greater…

  24. comment
    Comment #40456390

    The problem with nerd sniping is that it is instant gratification in a way. Always focusing on tech and math problems because you like solving them can lead to neglecting other are…

  25. comment
    Comment #40456150

    Not very theoretical. But with 'nerd sniping' focus I tended to create my own tech unnecessarily, and wasting too much effort to optimize things that do not necessarily need to be …