Live data from Hacker News

Viewing profile — immortalloom

immortalloom

HN member
Joined
Fri, Nov 04, 2011, 12:29 AM UTC
HN karma
218
Public activity
76 items

About immortalloom

No profile information was provided.

Recent public activity

  1. comment
    Comment #40789118

    Hi folks. The team at Vercel has a great guide for migrating CRA to Next.js manually ( https://nextjs.org/docs/app/building-your-application/upgrad... ). We converted this guide to…

  2. story
  3. comment
    Comment #37649044

    What are some other ones?

  4. story
    Three quotes that most accurately describe what it's like to build a startup

    "It's like chewing glass and staring into the void" - "It's like paving a road with your face" - "You wake up everyday and bang your head on the wall until something works"

  5. story
  6. comment
    Comment #37301745

    None come to mind - you should give it a go and see how the PR turns out

  7. comment
    Comment #37297327

    Yea that's the plan.

  8. comment
    Comment #37297125

    Hah yea. But, we use RAG to ensure that the choices made are really good. LLMs on their own can't be trusted, they are just great communicators. LLMs combined with reputable source…

  9. comment
    Comment #37296716

    Great question! So our AI agents actually use a combination codemods plus generated AI results. We use static analysis and codemods as much as possible, but there are lots of situa…

  10. comment
    Comment #37296427

    In general, as our AI agents produce code files, we collect dependencies, and then at the end, use npm to determine the correct version numbers without actually installing on disk

  11. comment
    Comment #37296366

    Yea! It turns out that we get this request quite often (Python 2 -> 3). It's on the roadmap.

  12. comment
    Comment #37296238

    We use LangChain to crawl documentation and code examples for relevant frameworks and libraries, to make sure that the AI generated PR is up-to-date. We also have a custom dependen…

  13. comment
    Comment #37296175

    Yea! Let me know if we can help your team with any of those. Right now we specialize in AngularJS -> React, CRA -> Next, JS -> TS, and Upgrade Next

  14. story
  15. comment
    Comment #36228743

    Beautiful! Insanely easy to use

  16. comment
    Comment #35089026

    Yes today the bots assume you are connecting to a Next.js 13 app. Bad assumption I know! I am working to add repo a scanner (ChatGPT prompts!) to understand the general tech stack …

  17. comment
    Comment #35089016

    Yes on both! 1) I will certainly work on setting up a show case or gallery of example sites 2) case study blogs are a great idea!

  18. comment
    Comment #35088291

    I believe that now is the perfect time. Generative code generation is legit with GPT-3. I am constantly surprised at the results. And it will only get better.

  19. comment
    Comment #35088263

    Yea great question! So yes, I used Second to build the foundation, auth, and DB stuff (starter plan stuff). But other parts of my app have not been ported back into modules yet (wh…

  20. comment
    Comment #35088070

    Correct! Second generates new features from configurable modules in the Second UI. I cannot use a prompt because this would require massive context windows (4k tokens is the limit)…

  21. comment
    Comment #35088050

    Yea, this is one of the capabilities I want to support. Auto upgrades. I am very confident it is possible, but it will be later on in my roadmap. Right now, most users and customer…

  22. comment
    Comment #35088036

    So the Second UI is based on feature modules. You, the human, choose a feature to add. You configure it and then press "Commit Code" or "Raise PR". You can customize in two ways: 1…

  23. comment
  24. comment
    Comment #35088010

    Agreed, we shall see! I empathize with what you are saying, because personally I am very slow to understand other people's code. But, because Second builds commodity features, ever…

  25. comment
    Comment #35087990

    Thanks! You're not wrong. A.I. is nothing more than an extension of our collective minds. If our collective minds are messy, the A.I. results will be messy as well.