Live data from Hacker News

Viewing profile — PhunkyPhil

PhunkyPhil

HN member
Joined
Wed, Jun 21, 2023, 8:50 PM UTC
HN karma
115
Public activity
77 items

About PhunkyPhil

No profile information was provided.

Recent public activity

  1. comment
    Comment #49022227

    Have they released the prompt they gave it in the debrief? I wouldn't be surprised if they said something to the effect of "Do anything you can to raise out of your sandbox. Find f…

  2. comment
    Comment #49007638

    This isn't that out there in our current scenario. These models compress our collective thought and effort. Why not make these publicly owned, all profits distributed back to us?

  3. comment
    Comment #48947985

    I knew I was a highlighter but reading that showed me how much my brain relies on spam click highlighting to keep my eyes on track. I should probably read more books.

  4. comment
    Comment #48922037

    I'm kind of in the same boat and it's been pestering me for months. Every agent is simply a less capable Claude Code. If it had a lossless, massive context window (100m-1b tokens),…

  5. comment
    Comment #48556428

    Prompt engineering is a skill insofar as technical communication is a skill. If you don't value this then I don't know what to tell you. It's not hard, but it's important. Harness …

  6. comment
    Comment #48467252

    School is almost a joke now. The fraction of students who have a propensity to cheat now has increased, and the accuracy of the cheated material is so good teachers/professors can'…

  7. comment
    Comment #48447835

    Obligatory taalas mention: https://taalas.com/ Despite the performative UI components they have a shipped (demo) product: https://chatjimmy.ai/ This is only 3.1 8B and a very small…

  8. comment
    Comment #48196680

    How does a grep or read affect the observing system? I guess the change in voltages, arrangement of registers, filling of buffers in the network stack are changing but... what?

  9. comment
    Comment #48135584

    > In distillation, you take a set of prompts you are interested in, and record the big LLM's outputs, then train your small model to produce the same output as the big LLM. Why use…

  10. comment
    Comment #48095851

    It's no secret they've been tracking people's faces as much as they can. The morning of Pretti I was on Lyndale and there were two men wearing "press" jackets with DLSRs taking pic…

  11. comment
    Comment #47938967

    The people controlling what went on the screens were unreliable and nondeterministic. The algorithm on facebook/instagram is nondeterministic and I hope I don't have to convince yo…

  12. comment
    Comment #47927396

    Right, but this electron box led to one of the largest (if not the largest) media revolution that has transformed the course of humanity in a frightening way we're still trying to …

  13. comment
    Comment #47867100

    _Nobody_ has the right take. Believe it or not, being seemingly laissez-faire about something can be a well evaluated and rigorous position. I highly doubt that OP doesn't care abo…

  14. comment
    Comment #47835516

    I'm still trying to understand how I feel about this so this is a bit of a napkin ramble; I can't help but feel like they've missed the mark a bit on some of the imagery from the m…

  15. comment
    Comment #47806826

    I can do you one better: ```python3 from openai import OpenAI import sys client = OpenAI() response = client.chat.completions.create( model="gpt-4", messages=[{ "role": "user", "co…

  16. comment
    Comment #47628234

    cybernetic culture research unit http://www.ccru.net I doubt it's currently maintained, but these esoteric sites are fun

  17. comment
    Comment #47503157

    Slightly off topic, but when I read about these archeological discoveries being made thanks to custom software, ML or the like - Who is writing this code? To me these projects woul…

  18. comment
    Comment #47139200

    Product owners and business people request code in vague English all the time. It's our job to parse it to code using our own judgement.

  19. comment
    Comment #47091667

    I think it's really useful for agent to agent communication, as long as context loading doesn't become a bottleneck. Right now there can be noticeable delays under the hood, but at…

  20. comment
    Comment #47091641

    I'm not saying you're wrong, but why is this the case? I'm out of the loop on training LLMs, but to me it's just pure data input. Are they choosing to include more code rather than…

  21. comment
    Comment #47049135

    I've been thinking exactly this. I'm a recent CS grad and have zero experience in anything physical or on the engineering side but I think I would enjoy it. I'm a bit intimidated b…

  22. comment
    Comment #45202084

    Fair enough. I will ask, how many billions have been spent in not only FSD but the car infrastructure that makes room for FSD investment? I'm being slightly fanatical, but if our p…

  23. comment
    Comment #45202035

    > It absolutely targets a problem that exists. Even in places with pretty great public transit, there is some demand for taxis/Uber/etc. Oftentimes even moreso, because if I don't …

  24. comment
    Comment #45201453

    This is true. Now to start a tangent, what's the easier problem to solve: FSD, or a robust public transport system? Moving rooms have always been around in the form of trains, buss…

  25. comment
    Comment #45201402

    FSD is not being marketed as an aide for elderly people or those with disabilities, it's being marketed as a panacea for all driving related problems