Live data from Hacker News

Viewing profile — typest

typest

HN member
Joined
Fri, May 03, 2019, 11:25 PM UTC
HN karma
789
Public activity
105 items

About typest

Contact: Jeremy.daniel.fox@gmail.com

Recent public activity

  1. comment
    Comment #40742936

    Hi! I’m a product engineer on the Claude.ai team. Claude.ai does support branching conversations. If you hover on a message, there should be an edit button, and once you edit the m…

  2. comment
    Comment #38839625

    I don’t want to die today, and tomorrow I’m not going to want to die, and the day after I’m not going to want to die, and so on. Therefore, I want to live forever — proof by induct…

  3. comment
    Comment #38552091

    If a model hasn't been explicitly told (via some system prompt or something) about its weights, it won't know them. It would be akin to asking you how many neurons you had. How wou…

  4. story
  5. comment
    Comment #37827449

    It seems to me that RAG is really search, and search is generally a hard problem without an easy one size fits all solution. E.g., as people push retrieval further and further in t…

  6. comment
    Comment #37398797

    I just got engaged. When we looked at rings, the jeweler asked my fiancé if she wanted natural or synthetic, and she responded “I don’t want a blood diamond!!” Of course, mined dia…

  7. story
  8. comment
    Comment #36142781

    Yes, PMF = "product market fit".

  9. comment
    Comment #36002415

    A city on its own generally has the power to change zoning and land use laws. There are limitations (some states give cities more or less power here) but generally cities do have t…

  10. comment
    Comment #35545522

    > All eligible entries must include either the word "wallabywinter" or the word "yallabywinter" (the “eligible keywords”) in one or more places as close as possible to the code. If…

  11. comment
    Comment #35454907

    It's not that they're just charging per token -- the actual models are operating on a token level. The model sees things in terms of tokens, and in openai's case, these tokens are …

  12. comment
    Comment #35277075

    This is not really true. The Chinchilla paper showed that a 4% difference in loss between Chinchilla and Gopher led Chinchilla to blow Gopher out of the water at most tasks, includ…

  13. comment
    Comment #35142692

    ^^ this. For instance, LLMs are really good at turning natural language into SQL. And if you know SQL, you can read it and make sure it looks good. But, it's much faster and easier…

  14. comment
    Comment #35115211

    Do you know of any advice or guides on how to use the chatgpt api? It's unclear to me when things should be a system message, and if not, if they should be user or assistant messag…

  15. comment
    Comment #34775961

    The other day, I was trying to build a web scraper, but I kept getting an error that the data wasn't utf-8 encoded. I gave chatgpt the error along with the first 10 bytes (e.g. b'\…

  16. comment
    Comment #34485682

    One tip to speed up how you're finding the closest matches -- openai's embedding vectors are normalized and all fall upon a sphere. So, the cosine similarity is equal to the dot pr…

  17. comment
    Comment #34153282

    I was also in STL when this happened. Had to drive 4 hours away to Evansville, IN in order to get a rental car. Just showed up here and they told me I was lucky to reserve it last …

  18. comment
    Comment #34096787

    This makes sense. And the game sounds really interesting! What is it called? I may try it out.

  19. comment
    Comment #34096766

    I mean, I don't really disagree with you. For sure, most all services have in the history of society been mostly, if not entirely, consumed by the rich. For most of society, most e…

  20. comment
    Comment #34095746

    Let's say there is a masseuse. They use their labor to give massages. They are also self employed, so they own their own business. If the cost of labor rises, the masseuse makes mo…

  21. comment
    Comment #34095466

    I think this makes sense with what I'm saying. Laborers get more of the profits of companies and in turn get wealthier. However, the costs of services in turn go up (due to rising …

  22. story
    Ask HN: What will everyone do if everything is automated?

    This is a question that I feel comes up a lot, and it's not often engaged with seriously. I feel sci-fi doesn't really engage with the concept (you'll get super smart AI, but someh…

  23. comment
    Comment #34095195

    There is a take that consistently comes up in discussions like this (and indeed is prominent several times on this post), which says "the problem isn't a shortage of workers, it's …

  24. comment
    Comment #33955407

    Other commenters arguing against you seem to be missing your point somewhat. I think right-sizing infrastructure to the community (and tax base) that supports it is a good and impo…

  25. comment
    Comment #33806702

    This isn’t true. Science is ultimately the scientific method — make a hypothesis, test a change, observe the results, repeat. It’s an algorithm for learning and broadly gaining inf…