AI CODING

Steve Yegge's Gas Town thesis is less about one tool than a shift from one coding agent to a durable, supervised colony of workers.

Steve Yegge's new essay argues that long-running coding-agent loops will push teams beyond reusable harnesses and toward bespoke, graph-driven software factories.

Steve Yegge's Flat Curve Society thesis turns the AI adoption question into an operating problem: teach people to use agents, then teach them to waste fewer tokens.

Steve Yegge's provocative model-welfare essay contains a practical systems idea: persistent agent roles need memory, graceful handoffs, and feedback from the people who use their work.

Steve Yegge's response to AI-generated pull requests suggests a better maintainer workflow: automate triage, repair good ideas, and keep human taste at the boundary.

Cursor shipped a deliberate change on July 31 making the Usage page tokens-only for self-serve plans, removed the dollar Cost column, and zeroed per-request cost fields in the dashboard API - including for historical records. Staff confirmed the change is intentional and that the numbers are still tracked internally.

A July 2026 Microsoft study of Claude Code and GitHub Copilot CLI found roughly 24% more merged pull requests among adopters, but the interesting lesson is rollout design, not magic productivity.

A practical guide to routing between Claude Opus 5, Sonnet 5, Haiku 4.5, GPT-5.6 Sol/Terra/Luna, and Kimi K3 based on task complexity, cost budget, and latency requirements - with decision frameworks and code examples.

Agent-Manager, Pane, and Golutra let you run multiple CLI coding agents in parallel. Here is the comparison of architectures, agent support, and which fits your workflow.

Belay, Claude Code built-in guards, Codex CLI sandboxing, and MCP proxy patterns compared - how to protect your system from destructive commands, secret leaks, and prompt injection in AI coding agents.

How Claude Code, Cursor, Codex, GitHub Copilot, Aider, and Windsurf handle permissions, sandboxing, credential protection, and prompt injection. A structured comparison for engineering teams evaluating agent security.

Tom Lockwood investigated the Bun Rust rewrite six weeks after it merged to main - 2,475 open PRs, no release tag, and costs that may far exceed the claimed $165K. We break down the evidence, Jarred Sumner's response, and what the HN community thinks.

The late-July Codex and Claude Code updates point in the same direction: coding agents are competing on approval modes, resumable work, MCP auth, artifacts, and review surfaces as much as raw model quality.

Ruff v0.16.0 ships 413 default rules (up from 59), Markdown code-block formatting, and a new ruff: ignore system. Here is what changed, what HN is saying, and why zero-config linting matters more with AI coding agents.

Replit Agent 4 adds an infinite design canvas, parallel agents, and team collaboration to the prompt-to-app platform. Here is what changed, what it costs, and when to use it.

Claude Opus 5 ships today with Frontier-Bench SOTA, near-Fable-5 coding at half the price, and self-verification that catches its own bugs. Here is what changed, what to migrate, and when the price-performance curve makes Opus 5 the right default.

The DataFlow-Harness paper is a useful reminder that coding agents should not just emit scripts. For data work, the durable artifact is an editable, validated pipeline.

A deep dive into why fully autonomous AI coding agents degrade codebases over time, and what context engineering can actually fix.

Where to access Kimi K3: Moonshot's API at $3 input and $15 output per million tokens, OpenRouter hosts, inference clouds, and open weights.

Cursor's latest agent-swarm experiment rebuilt a SQLite-like database from documentation and passed a held-out conformance suite. The bigger story is the shift from assigning code tasks to specifying, measuring, and governing a goal.