Live data from Hacker News

Viewing profile — raghavchamadiya

raghavchamadiya

HN member
Joined
Mon, Jan 05, 2026, 11:30 AM UTC
HN karma
13
Public activity
16 items

About raghavchamadiya

Building and breaking software. Currently thinking a lot about AI agents and developer tools.

Recent public activity

  1. story
  2. story
  3. story
  4. comment
    Comment #48256836

    That smell thing is so real. I still get hit with it randomly and I'm immediately 10 years old again

  5. comment
    Comment #48256815

    Nice to see this getting the Jupyter Notebook treatment. The original book was already one of the better introductions to APL. Interactive examples make a huge difference for a lan…

  6. comment
    Comment #48210972

    Wild how fast this moved from "capped profit" to full profit conversion to IPO. Wonder what the final valuation lands at given how fast they're burning cash

  7. comment
    Comment #48210917

    This is actually scary. If Google can suspend a company like Railway without warning, what chance does a smaller startup have? The lack of any human escalation path at Google Cloud…

  8. comment
    Comment #48189972

    [flagged]

  9. comment
    Comment #48168473

    [flagged]

  10. comment
    Comment #48168418

    [flagged]

  11. story
  12. story
    Show HN: Repowise – Codebase intelligence for AI coding agents (open source)

    Every AI coding session starts from zero. The agent doesn't know who owns a file, which files change together, which ones are dead, or why something was built that way. I got tired…

  13. story
  14. story
    What happens to an economy when AI makes most human labor optional

    I keep seeing two extreme futures discussed around AI. One is techno utopia: AI does everything, productivity explodes, humans are free to create and chill. The other is collapse: …

  15. story
    Agentic Frameworks in 2026: Less Hype, More Autonomy

    Over the last two years we have gone from “LLMs with tools” to genuinely agentic systems that plan, reflect, delegate, retry, and sometimes surprise us in ways that feel uncomforta…

  16. story
    What breaks first when you try to build real world AI agents

    I’ve been working on AI agents outside of demos and toy tasks, and a pattern keeps repeating: the first things to break are rarely model quality. A few failure modes showed up almo…