Live data from Hacker News

Viewing profile — shivang2607

shivang2607

HN member
Joined
Sat, Nov 15, 2025, 6:54 PM UTC
HN karma
12
Public activity
72 items

About shivang2607

I am a Software Engineer, trying to build things which people might actually find useful.

Recent public activity

  1. comment
    Comment #49234985

    Currently working on Intelligent Codebase Visualizer for reactjs/Nextjs/js and ts Codebases for easy PR review, easy onboarding and easy PR review. Github: https://github.com/devle…

  2. comment
    Comment #48919284

    I am building an open source codebase vissualizer for devs and AI agents(to provide graphical context to them) with features like impact analysis, blas radius, PR review etc. It is…

  3. comment
    Comment #48670784

    I think people have started to liek TUI applications since Harnesses have started working through the terminal

  4. comment
    Comment #48537549

    I am working on devlens.io , It automatically maps your codebase dependencies and drops precise structural insights directly into your GitHub PRs. No hallucinations, just hard cont…

  5. story
    Mimo v2.5 is better deal than DeepSeek v4 flash

    So Hear me out. Not only on almost all benchmarks is mimo v2.5 is better than dsv4f flash, but also the pricing. Most people only look at input and output cost of the model, what t…

  6. story
    Ask HN: Which AI harness comes close to Claude Code?

    I really want to try deepseek V4, but harnesss which I have previously used are inferior than Claude Code. Please suggest some Harnesses here. I have tried, roo, cline, opencode

  7. comment
    Comment #48175975

    Maybe, in your experience, but I have tried both claude and codex and the code quality that claude produces is still superior in my experience, maybe its because of the nature of a…

  8. comment
    Comment #48145912

    In my personal experience, no model comes close to claude when it comes to coding performance. It does not matter what any of the benchmarks says. Having said that I really hope th…

  9. comment
    Comment #48145859

    Currently Working on https://devlens.io which is an Open source Intelligent Codebase Visualizer for javascript, Reactjs, nextjs and nodejs for easy onboarding and easy PR review. T…

  10. comment
    Comment #48125898

    Also the main MOAT of Devlens is not the visualizer but the blast radius feature. Which essentially tells you if I change this file/function where it will affect my Codebase which …

  11. comment
    Comment #48125882

    Currently Working on https://devlens.io which is an Open source Intelligent Codebase Visualizer for javascript, Reactjs, nextjs and nodejs for easy onboarding and easy PR review. T…

  12. comment
    Comment #48110879

    While working with larger React / Next.js codebases, I noticed a lot of PR review time goes into understanding the impact of a change rather than the change itself. Things like: wh…

  13. story
  14. comment
    Comment #48099337

    While working with larger React / Next.js codebases, I noticed a lot of PR review time goes into understanding the impact of a change rather than the change itself. Things like: wh…

  15. story
  16. comment
    Comment #48099327

    Something which is really technical, and complex enough that not many people can do that. And ofc it should earn be handsome money :)

  17. comment
    Comment #48099316

    Been working on a tool called Devlens. It visualizes React / Next.js codebases as an interactive graph so you can understand how features and components connect without manually tr…

  18. story
    Ask HN: Would you use a "blast radius" view during PR reviews?

    I’m building a tool around this idea and wanted to sanity check it. In larger React / Next.js codebases, PR reviews often feel less about the change itself and more about understan…

  19. comment
    Comment #48005758

    Getting too much dependent on LLMs will eventually rust out my brain. I started notificing using tools like claude code and cursor, is ontroducing blackbox around architecture arou…

  20. comment
    Comment #47990429

    [flagged]

  21. story
  22. comment
    Comment #47980992

    I like the Irony with the Names

  23. comment
    Comment #47958727

    what do you mean by "still" ? Did people even used it ?

  24. comment
    Comment #47954204

    [flagged]

  25. story