Live data from Hacker News

Viewing profile — colinator

colinator

HN member
Joined
Tue, Nov 08, 2016, 1:23 AM UTC
HN karma
45
Public activity
34 items

About colinator

No profile information was provided.

Recent public activity

  1. comment
    Comment #49089777

    I concur. Most of my MCP pain is dealing with client's differing ability to handle images. Some clients (old codex) would even truncate the base64 data regardless of how it was jso…

  2. comment
    Comment #48597341

    Good move getting a nice robot! I'm doing something similar to you, but I went with a cheap robot, the "HIWONDER 6DOF Robotic Arm Kit". It was only $600, but wow is it bad. The pre…

  3. comment
    Comment #47784807

    That video is pretty good, thanks for finding it. I'm basically betting that an earlier, abandoned approach described in the video, "Code as Policy", will beat everything else. It …

  4. comment
    Comment #47783345

    I was also just in the market for a small experiment robot. I got the hiwonder armpi-fpv. Avoid it, the actuators are pretty bad - they're very 'grindy', the robot jitters like cra…

  5. comment
    Comment #47783177

    For the fine-motor commands: or, the model can write the code to generate them on the fly. It seems to work, in my very limited experiment. As for memory: my approach is to give th…

  6. comment
    Comment #47782557

    This seems perfect to hook up to my 'LLMs can control robots over MCP' system. The idea is that LLMs are great at writing code, so let's lean in to that. I'll give it a try! I just…

  7. comment
    Comment #47747262

    Remember how all those years ago (oh wait, a few months ago), that big npm hack attack was found by someone thinking their ssh connection was half a second too slow? Hope this ain'…

  8. comment
    Comment #47746966

    Yeah, the mechanism by which the LLMs control the robot is by writing code. I suppose they could also issue direct joint sequences, but I thought that they're so good at writing co…

  9. comment
    Comment #47746754

    I'm connecting LLMs directly to robots, to see how well they can perform robot things by directly controlling motors and sampling the camera/sensors. Initial results are encouragin…

  10. comment
    Comment #47739869

    Here's an idea for how to do that: treat frontier AI as a sort of 'common carrier'. The only business that frontier AI labs are allowed to conduct is selling raw tokens - no UI. Th…

  11. story
    Show HN: Ariel gives LLMs direct control over live robots

    Hi all! I created 'Ariel', an MCP-exposed python REPL for LLMs to directly control robots. The basic idea is: the most impressive ability of contemporary AI is not predicting the n…

  12. comment
    Comment #47387303

    Yet another problem with MCP: every LLM harness that does support it at all supports it poorly and with bugs. The MCP spec allows MCP servers to send back images to clients (base64…

  13. comment
    Comment #47335928

    I've got one of these! Mine is called 'roboflex' (github.com/flexrobotics). It's c++/python, not rust. But similarly born out of frustration with ros. Writing your own robotics mid…

  14. comment
    Comment #42589849

    A few years ago there were actually two companies trying to manufacture "zblan optical fiber" (which has better light transmission than normal optical fiber) in orbit: Made In Spac…

  15. comment
    Comment #41768008

    Borges: Selected Non-fictions. Think his fictions are good? His non-fictions, imho, are even better. You can read three sentences and feel like you just listened to a symphony - yo…

  16. comment
    Comment #41606388

    I did some robotics tactile research, it was super fun! We used "biotac" sensors, which are very capable, but are 1) crazy expensive and 2) crazy hard to replace the skins, which d…

  17. comment
    Comment #41567243

    Here's another one: "roboflex", https://github.com/flexrobotics ROS is irredeemable. I've seen it used in large projects, and the amount of time wasted "wrestling with ros" was rid…

  18. comment
    Comment #39633430

    Well, our brains are closer to spiking neural networks than 'regular' neural networks. And they work pretty well. For the most part. I feel like SNNs are like Brazil - they are the…

  19. comment
    Comment #37863635

    Robotics middleware: https://github.com/flexrobotics/roboflex Basically a simpler version of ros. Easily, and performantly (is that a word?) connect cameras and other sensors, via …

  20. comment
    Comment #21232929

    Well, at this point the GOP is fully deserving of shame. Are they coming up with a grand plan to solve climate change with a new nuclear industry? If so, I'd love to hear it! But s…

  21. comment
    Comment #21232881

    [flagged]

  22. comment
    Comment #21232761

    Oh yeah, "politely waiting". You mean "denying the very existence of a problem". Meanwhile: is it? How do you know?

  23. comment
    Comment #20575009

    I'm curious about this as well. It's now #69, 5 minutes later. I seem to recall this happening quite a bit for global warming stories. Anyone from HN want to explain please? Do all…

  24. comment
    Comment #20574943

    What if there were a border-adjustment carbon tax? So countries that emit a lot of CO2 get taxed into oblivion? That's a thing we could do... (_will_ do: another story)

  25. comment
    Comment #19859663

    Yeah, totally! You can find me email from my github profile.