Live data from Hacker News

Viewing profile — taherchhabra

taherchhabra

HN member
Joined
Tue, Jun 19, 2012, 10:33 AM UTC
HN karma
75
Public activity
87 items

About taherchhabra

Building flickspeed.ai

Recent public activity

  1. comment
    Comment #48052617

    I wrote something recently on how agent development differs from traditional software development https://x.com/i/status/2051706304859881495

  2. comment
    Comment #47757265

    Canvas for context management

  3. story
    Show HN: The Harness for Creative Agents

    Coding agents need shell. Creative agents need canvas. Flickspeed gives image, video, audio, and research agents a shared workspace to direct, iterate, and ship together.

  4. comment
    Comment #47748538

    Genuine question. After claude code, codex etc, can't this be speedup ?

  5. story
  6. story
  7. story
  8. comment
  9. comment
    Comment #46785291

    I am building flickspeed.ai where you can build a pipeline in plain english. Let me know if you'd like to have a demo

  10. comment
    Comment #46729954

    I want to build my own video model, just for learning purposes, is there any course which can teach end to end

  11. comment
    Comment #45954577

    yes agree, and that has been my learning as well.in the current version of the product, the end user does not need to know about the nodes and other complexity, instead can use var…

  12. comment
    Comment #45948236

    I am building one such tool. Flickpseed.ai Give it a shot

  13. comment
    Comment #45873018

    Building https://flickspeed.ai Its cursor for creativity.

  14. comment
    Comment #45690526

    I am building https://www.flickspeed.ai using this library

  15. comment
    Comment #45612989

    Can I run claude code or codex inside this

  16. story
    Show HN: Infinite canvas for AI media generation

    one-off image/video generation is easy, but creating a cohesive story with consistent characters and locations across multiple scenes is difficult. So I am building flickspeed.ai w…

  17. comment
    Comment #45577919

    I don't think the models are dumb anymore, codex with gpt5 and claude code can design and build complex systems. The only thing is these models work great on greenfield projects. L…

  18. comment
    Comment #45564755

    I am working on a infinite canvas for AI image/video/audio/3D generation. in other tools, its easy to create one off AI images/videos, but to create a cohesive story with consisten…

  19. comment
    Comment #44963896

    so beautiful. thank you for this. I am trying to develop intuition for sine cosine etc. and it did fire some neurons in my brain not sure i can put that into words

  20. comment
    Comment #44897760

    Just yesterday my son built a zombie shooter game in chatgpt, then shared the link with his friend, both were able to play individually, then my son asked can we play together and …

  21. comment
    Comment #44708543

    At my ex employer, every employee had an hourly rate in the system, I had thought of pulling the rates from the internal system into Microsoft teams, to display the cost of every m…

  22. comment
    Comment #44673201

    Sometimes Claude code defaults to using the older versions of certain libraries, have to explicitly tell claude to use the specific version. Even then it goes back to older version…

  23. comment
    Comment #44536359

    I've created a comparison canvas with before/after results testing Flux Kontext Image editing across 13+ editing scenarios. The model's contextual understanding is surprisingly goo…

  24. story
  25. comment
    Comment #44053352

    thanks for this insight