Tag
A developer describes their first use of agentic coding in a physical installation project, noting how it dramatically reduced the time for complex tasks involving hardware and software integration.
Garry Tan endorses Capy, a tool that enables faster creation of pull requests compared to using Codex or Claude Code alone.
A developer uses Claude and other AI models to build a custom watch face for the PineTime smart watch, leveraging open-source firmware and simulators for an AI-assisted hacking project.
A user created a simple game with just two prompts using the Qwen 3.8 AI model in Q4 quantization on llama.cpp with dual RTX 3060 GPUs, demonstrating impressive AI-assisted coding despite RAM limitations.
An opinion piece discussing the Bun migration from Zig to Rust, Andrew Kelley's critical response, and a broader philosophical debate about whether software engineering is a craft or industrial process.
Jaithon 3 is a dynamically executed and garbage collected programming language that merges the best parts of Java, Rust, and Python, with AI-assisted coding used in its development.
A non-engineer shares that the biggest pitfall in AI-assisted 'vibe coding' isn't prompting but verifying whether an AI fix truly solves the root cause or just patches a specific case, leading to fragile code. Offers practical tips like asking if a fix is general or special-cased, and maintaining a living design doc.
A tweet reports that Super Smash Bros Melee was decompiled and reverse engineered into about 5000 lines of C using DeepSeek Flash 0731 on a phone, while taking care of a newborn.
A blog post shows that a formally verified Lean implementation of DEFLATE compression outperforms a pure-Rust implementation in both speed and compression ratio at typical levels. The author attributes this to the ability to safely let AI agents optimize the code, relying on the formal proof to guarantee correctness.
This guide explains how to evaluate the quality of AI-generated code using tests, golden datasets, reliability checks, and human review. It provides a practical workflow for catching regressions and shipping AI-assisted code with more confidence.
In the age of AI-assisted coding, the author argues that deep understanding of programming language concepts remains essential for engineering, listing key ideas from various languages that expand mental models for problem solving.
Honeycomb's engineering team more than doubled peak daily merges from ~30 to ~74 using AI tools like Claude Code, with AI-attributed code rising to 82.6% by June 2026, while managing incidents proportionally. They share practices like continuous delivery, fast CI, and observability that amplified with AI.
A developer built a full 3D open-world racing game with AI assistance, detailing where AI excelled (boilerplate, isolated systems) and where it failed (spatial reasoning, system integration, game feel). The game is live with real daily players.
In this blog post, antirez argues that in the age of AI, programmers should focus on controlling the ideas behind their software rather than reading every line of code, as AI can generate locally optimal code but humans excel at big-picture design and direction.
The article warns that relying on LLMs to write code without maintaining good patterns teaches the AI bad habits, leading to a codebase full of duplicated logic and ever-worsening code quality.
An open-source CLI tool scans Python, JavaScript, and TypeScript projects to identify modules and provide architecture metrics, with AI assistance for coding.
A Hacker News user asks the community about experimental approaches to using LLMs for coding, expressing frustration with current prompt-response loops and seeking fundamentally different methods.
A discussion about using AI Agent for system design and coding in a microservices environment, highlighting the need for the AI to understand service boundaries and business concepts.
VikingMute shares their main workflow for developing new features and ideas: using AI (Grill) to drill down on details, Research to analyze difficulties, generating a PRD, breaking it into independent Issues, step-by-step implementation, and finally Review. This is a supplement to Matt Pocock's seven-stage AI development method.
A developer shares their weekend project of building a low-level infix language that compiles to WebAssembly, and offers a personal ranking of AI coding tools from contextual autocomplete to frontier models.