Live data from Hacker News

Viewing profile — crosen99

crosen99

HN member
Joined
Mon, May 23, 2022, 4:55 PM UTC
HN karma
157
Public activity
76 items

About crosen99

No profile information was provided.

Recent public activity

  1. comment
    Comment #41754477

    I got off a quick GPT trying to explore the following theme, and I think the results are promising: In the ever-evolving landscape of creative expression, a new horizon emerges: AI…

  2. story
    Show HN: Custom GPT demonstrating a new genre

    Hi all - I got off a quick GPT exploring the following theme, and I think the results are promising: In the ever-evolving landscape of creative expression, a new horizon emerges: A…

  3. comment
    Comment #38475975

    Well said, and fully agree. If you horse race two approaches, you can of course arbitrarily arrive at a winner based solely on the version of each approach you choose. You need a d…

  4. comment
    Comment #38171554

    They stumbled into a position where they can make a crap ton of money going up the stack, which can fund the ongoing march toward AGI. (The revenue not only is cash in their pocket…

  5. comment
    Comment #38127741

    > we've heard that when people were using chains/agents they often wanted to see what exactly was going on inside, or change it in someway. I certainly agree, but I'm having troubl…

  6. comment
    Comment #37162932

    The biggest challenge I’m trying to track isn’t on the list: online learning. The difficulties with getting LLMs to absorb new knowledge without catastrophic forgetting is a key fa…

  7. comment
    Comment #36747534

    You might wonder if these harbingers are actually tuned into an alternate and consistent set of values not shared by the majority, rather than simply irrational consumers. In that …

  8. comment
    Comment #36747442

    Same here. I think it's because you typically conquer a language by developing a fairly complete mental model of that language's behavior, but with CSS there are just too many nook…

  9. comment
    Comment #36648378

    I keep going back to LangChain thinking it just hasn't found its legs yet, but every time I do I retreat exasperated. I don't find their abstractions useful or intuitive, and their…

  10. comment
    Comment #36632704

    Strong disagree. The way I see it, any successful customer service operation needs to have three things in place: 1. Properly defined and articulated customer service policies and …

  11. comment
    Comment #36587689

    > AIs, at their current level of development, don’t perceive objects in the way that we do – they understand commonly occurring patterns. You see this claim everywhere - that AI op…

  12. comment
    Comment #36357094

    Not substacks, but I start my mornings reading the TLDR and the TLDR AI newsletters. Lots of overlap with the sort of tech that HN covers. TLDR AI is very useful to keep your finge…

  13. comment
  14. comment
    Comment #36232056

    This “new technique called implicit code execution” sounds a lot like an early version of the ChatGPT Code Interpreter plug-in.

  15. comment
    Comment #36227853

    I wanted to give this a whirl by creating an event triggered workflow, but I got stuck pretty quickly. I had imagined creating a workflow that would be triggered by the occurrence …

  16. comment
    Comment #36113734

    "Radiologists are not performing 2d pattern recognition - they have a 3d world model of the brain and its physical dynamics in their head. The motion and behavior of their brain to…

  17. comment
    Comment #36100216

    That article links to the below article where Musk lays out his version of the simulation argument. His version is fraught to the brim with confused thinking and non sequiturs, and…

  18. comment
    Comment #35982315

    I'm surprised not to see anything about data-to-parameter ratios for optimal scaling. My superficial understanding per the Chinchilla paper is to target 20 to 1. I'm also confused …

  19. comment
    Comment #35668718

    Could you link to your research and/or describe the models, libraries, data and tests you used for this?

  20. comment
    Comment #35667178

    It's amazing how much misinformation and vague information there is on this topic. I tried getting to the bottom of this in the following post in the OpenAI forum: https://communit…

  21. comment
    Comment #35640499

    LLM based autonomous agents remind me a lot of Leonard from the movie Memento. In the movie, Leonard is trying desperately to find the murderer of his wife, but he has one big prob…

  22. story
  23. comment
    Comment #35389506

    You'd have to be naïve to deny that AI poses a risk that must be taken seriously. But, to think that a moratorium - which would be ignored by those with the greatest likelihood of …

  24. comment
    Comment #35342823

    In addition to the choices for how to chunk (i.e. defining chunk size, chunk boundaries, chunk overlap, etc.), there's also the question of what actually gets returned once finding…

  25. comment
    Comment #35342411

    The problem I'd like solved is that when I want to retrieve chunks of data for retrieval augmented generation, it's challenging to optimize the choice of embeddings model, chunking…