Live data from Hacker News

Viewing profile — kagevf

kagevf

HN member
Joined
Tue, Mar 12, 2013, 5:09 PM UTC
HN karma
260
Public activity
291 items

About kagevf

Learning Common Lisp along with Parenscript. Day job using C# on asp.net (core). Also dabble in reactjs and F#

Recent public activity

  1. comment
    Comment #49116801

    For sure. Its code output is definitely not to be fully trusted. Oftentimes, you can point at where it made a mistake and it usually fixes it too.

  2. comment
    Comment #49115968

    > That’s not necessarily a bad thing. True, and to my point, "popular" isn't necessarily "better". > because they are so standard and are good enough, using them massively eases th…

  3. comment
    Comment #49114866

    > Next up is demonstrating the AI is more productive with better programming languages. That actually would be pretty exciting! But, wouldn't AI be biased toward more popular langu…

  4. comment
    Comment #48532732

    Apparently, the Series library offers that. It didn't make it into the ANSI standard, but it's still maintained and covered in CLtL2. edit SICP has examples on how to implement str…

  5. comment
    Comment #46592116

    From what I've seen, "AI" is typically written with the "Roman" (latin) letters, or translated as 人工知能 (AI) or as 生成AI (generative AI like LLMs).

  6. comment
    Comment #46296636

    Wikipedia is right; the romanization is just matching how it's rendered in kana.

  7. comment
    Comment #46109787

    I think your post pretty well illustrates how LLMs can and can't work. Favoriting this so I can point people to it in the future. I see so many extreme opinions on it like from how…

  8. comment
    Comment #45482922

    One approach would be to write code first, then run it by AI to get a critique. I think that strikes a good balance between avoiding atrophy and still getting the benefits of the t…

  9. comment
    Comment #44964427

    If I create an executable with SBCL's save-lisp-and-die then run that executable, it presents a repl. Not really a development scenario, but more of a "running application" scenari…

  10. comment
    Comment #44833091

    When I saw the headline, I thought it referred to "Q" the array programming language (looks like your first link).

  11. comment
    Comment #44595773

    I didn't know about M-? ... I like how if there's only 1 match it automatically jumps to that single reference. :)

  12. comment
    Comment #44500105

    I liked the convention of putting the TLD in parentheses after each link.

  13. comment
    Comment #44032958

    May 19 and May 20.

  14. story
  15. comment
    Comment #43988879

    > "Anything with non-deterministic output will have this. Anything with non-deterministic output that charges money ... Edit Added words to clarify what I meant.

  16. comment
    Comment #43918611

    > EDIT: It has been brought to my attention that these misclicks/mistaps are a source of ad revenue haha ... looks like "follow the money" applies yet again to get to the root caus…

  17. comment
    Comment #43906164

    Maybe substack?

  18. comment
    Comment #43892498

    Thank you, I'll check it out!

  19. comment
    Comment #43892018

    I like LoL alright too. I was only maybe a year or so into CL when I read it, so I didn't really notice a lot of what it's criticized for. On the one hand, I'm a little sad that I …

  20. comment
    Comment #43891619

    Here's an example: http://metamodular.com/Books/land-of-lisp.html

  21. comment
    Comment #43890371

    My opinion of LOOP started to change when I read (the much maligned) "Land of Lisp" and went over that "periodic" diagram in TFA. Seeing the elements of LOOP broken down like that …

  22. comment
    Comment #43797912

    Sometimes harsh language is required to help the customers realize how ungrateful they truly are.

  23. comment
    Comment #43734418

    thank you!

  24. comment
    Comment #43730453

    Care to share your .emacs? :)

  25. comment
    Comment #43688142

    > There is no such thing as an LLM 'session'. This matches my understanding too, at least how it works with Open AI. To me, that would explain why there's a 20 or 30 question limit…