Pewarta Proxy

📋 Server Request & Proxy Logs

Loading active proxy settings...
Developed by Khairul Adha (adhexa.id)
Mengambil log server...

⚙️ Pengaturan Proxy Target

Skip to content

AI usage memo #1624

Open
Open

Description

@stonebig

recipes, from time-consuming experience

errors:

  • prompting too simple: the AI doesn't respect any rule and can change things you don't want at first (like variable names)
  • not using multi-AI loost the comparison and compensation (like orthographic errors, what is generated different is what to look)
  • an easy before/after comparison test is usefull, better when they can auto-check themself, simpler if they write auto-test
  • not adding safe exit to llm , "do you think it's possible ? is there enough information to", may reduce hallucinations
  • accepting torents of lines of code... as AI can bloat you also on this

total time saver:

  • asking AI to not disrupt existing code: "can you help rework it so it can do current feature and new one ?"

next level things:

This parodic picture summarizes well the standard pitfalls when using IA too blindly

Image

Activity

  1. pinned this issue on May 30, 2025
  2. stonebig commented on May 30, 2025

    @stonebig
    ContributorAuthor

    diff.py:
    let's try to use AI in a smarter way:
    - run current and proposals from openai, copilote, mistralai, gemnicodeworks
    - compare results (accept slight massage at interface naming, output must be same as original)
    - compiles without hurting much interface: openai,, gemini
    - don't crash and result ok: openai,
    - crash and burn : gemini, mistralai
    - change interface (remove a parameter): copilote
    - lines_of_code (ignoring commente of gemini): original: 170 , openai: 129, copilote: 98, mistralai: 161, gemini: 350

    in the end, still 1 day to:
    - digest the AI change
    - then do the re-engineering to move diff.py down

  3. stonebig commented on May 31, 2025

    @stonebig
    ContributorAuthor

    package_index_markdown (try on copilote, as move of code between the project files)

    i would like to have the core part of the "package_index_markdown" function pushed from make.py down to wppm.py. 
    Goal is to have less things in make.py, and more in wppm.py so most of the feature is available from wppm 
    

    proposed the stupid/basic solution, good here

  4. stonebig commented on Jun 1, 2025

    @stonebig
    ContributorAuthor

    adding safe exit to llm , "do you think it's possible ? is there enough information to", may reduce allucinations

    to copilote:
    could we make piptree working either on current installeed packages, either in a directory of packages ? it seemes all we need is reading the metadata from the archive like wheelhouse.py does

    gives a general structure that works, but prefer doing integration by hand so far

  5. stonebig commented on Jun 7, 2025

    @stonebig
    ContributorAuthor

    asking an AI (copilote github) to take care not disrupting existing code... does work!

    I would like the diff.py program to be usable to compare  two given markdown files, currently it's doing it's own scanning of directory... can you help rework it so it can do current feature and new one ? ````
    
  6. stonebig commented on Jun 29, 2025

    @stonebig
    ContributorAuthor

    the two most eminent uv people use AI (typically Claude, at the moment)... maybe also because with AI, the slowness of alternatives becomes the main time-loss/cost factor in their workflow.

    Agentic Coding: The Future of Software Development with Agents

  7. unpinned this issue on Aug 14, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions