Birbla

Discussion summary

The discussion covers the development of Claude Code, with some highlighting technical challenges and historical context. Users express skepticism about autonomous coding claims and compare it to simpler solutions.

What the discussion says

  • Tristan Hume reports persistent issues with Claude Code.
  • Some users question the feasibility of autonomous software engineering.
  • Criticism of Claude's performance compared to simpler tools like Pi.
“This thing just doesn't work…”
— mccoyb
“Claude Code is the latest step in AI coding evolution.”
— lifthrasiir

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • > I had written a whole pull request by hand, and then Adam rejected it. But he said, “Actually, you should use clide for this.”

    Interesting

    by ryanschaefer
  • Incredibly cringe. Literally every single medium mode problem for a team is framed as a groundbreaking achievement. These people snort their own farts.
    by hatefulheart
  • Once you are popular, whatever said is automatically true
    by a_c
  • Claude itself (Opus) gave me the following conclusion:

    > The article frames Claude Code as the latest step in a lineage from punch cards → ed → modern editors → AI agents. Multiple team members say they no longer write any code by hand. The overall tone is "we built the right primitive (read/edit/bash), bet on future model improvements, and it paid off."

    Honestly I don't want to endure an awkward terminal interface and/or questionable design to just arrive at this conclusion.

    by lifthrasiir
  • Pi was written by like one guy and it's better than this
    by xyzsparetimexyz
  • The self-mythologising is strong with this one...
    by alpineman
  • Nauseating on so many levels. What are we celebrating, even? Authors themselves say that Claude does their work, so what is their input? It's been barely a year in production for what can be best described as a 'buggy mess'.
    by xpct
  • Aider was also some of the most amazing prior art. After switching from the early copilot (crazy to think they were first to market with this stuff?) it was an amazing TUI experience. CC won because it offered token hungry devs a fixed price for almost infinite usage in the early days with stacks of VC cash to burn.
    by chrisvenum

Explore Birbla archives