Live data from Hacker News

Viewing profile — hidelooktropic

hidelooktropic

HN member
Joined
Fri, Oct 22, 2021, 2:29 PM UTC
HN karma
475
Public activity
241 items

About hidelooktropic

meet.hn/city/us-San-Jose

Socials: - github.com/adamjgrant

---

Recent public activity

  1. comment
    Comment #49233913

    You can plug it in

  2. comment
    Comment #49134255

    I like the AI overviews.

  3. comment
    Comment #48934616

    I like the idea but it takes a lot of thinking power that I have to come up with actual words that long each time.

  4. comment
    Comment #48885280

    They are just making the point that it makes sense that subagents would use more tokens because they have none of the parent's context.

  5. comment
    Comment #48584695

    I can talk faster than I can type.

  6. comment
    Comment #48580307

    Here is the music from the video: https://music.apple.com/us/album/on-an-evening-at-the-lake-f...

  7. comment
    Comment #48575791

    Wow. That's fascinating. Thanks for that explanation. So these images come to be consequentially from initial state and weights...

  8. comment
    Comment #48575226

    Especially for fable, that's not a fair comparison.

  9. comment
    Comment #48569582

    For the unfamiliar, could someone explain what I'm looking at? The abstract was a little too concrete (heh) for me to follow.

  10. comment
    Comment #48504255

    It's just Facebook.

  11. comment
    Comment #48309624

    You make a good point that not having it is easy to spot. But what precisely would flip the switch? Seducing someone for example, how often would that have to work? On all people? …

  12. comment
    Comment #48309491

    > The overlapping AGI definition I use here is "Most purely cognitive labor is automatable at better quality, speed, and cost than humans". For some of these researchers, saying th…

  13. comment
    Comment #48161019

    I guarantee you no one is working on this.

  14. comment
    Comment #47674909

    I don't know what you're talking about. I always reserve right up to the knife's edge of what I actually use.

  15. comment
    Comment #47401622

    Oh relax. Let people make things. It's okay to have more than one take on an idea.

  16. comment
    Comment #47241390

    I understand the article is actually not about support chatbots specifically but seeing the conversation here talked about that it's not out of place to join in that discussion. At…

  17. comment
    Comment #47241303

    I agree that's why I would prefer to have AI if it does the job better and if it can be further trained to understand when to escalate in the case of a more technical user which I …

  18. comment
    Comment #47240756

    It matters less to me that the helper is an AI/human than the kind of help I'm getting. The bigger problem to me is "help" is always framed as my needing to be educated, not a prob…

  19. comment
    Comment #47221347

    There are many concerns and areas for improvement with open claw and other similar projects (continuous loop script with broad OS access that manages your agents and interfaces wit…

  20. comment
    Comment #47219260

    The whole point is to measure your hardware capability. How would you do that as a website?

  21. comment
    Comment #47219211

    So you do things one step at a time and timebox as you go? This method probably doesn't need its own name. In fact I think that's just what timeboxing is.

  22. comment
    Comment #47219144

    Not sure what you have against it. Works great for me. No subscription required. And if I do want to pay for ad free shows and support creators it's easy to do so. Use whatever you…

  23. comment
    Comment #45929934

    Yes. I want AI in some things (some)

  24. comment
    Comment #45838413

    You might want to review the influence of William the conqueror on the English language.

  25. comment
    Comment #45739086

    How can I get early access to this "Human" model on the benchmarks? /s