Topic

#Ai Coding

38 articles on Ai Coding — news, releases, guides and analysis from the SourceFeed engine.

Article 1w ago 2

AI Didn't Wreck Your Codebase. Your Review Budget Did

GitClear, DORA, and METR data show AI-era tech debt is real and measurable — and slowing down is the wrong fix.

Mariana Souza

Your Management Playbook Assumed Code Was Expensive

DORA, GitClear, and METR data all confirm the bottleneck moved from writing code to verifying it.

Article · 1mo ago0

Better Than a Compiler, Trusted Like One

exe.dev's case for not reading AI-generated code is the sharpest yet, but it borrows a guarantee LLMs don't offer.

Article · 1mo ago4

GitHub's Copilot SDK Puts Agents in Your Stack

Six language clients expose the same agent runtime as Copilot CLI, so apps can ship planning and tools without building orchestration.

Article · 1mo ago7

Microsoft's CLI Agents: Social Spread, Real Lift, Real Cost

A rare internal study plus a hard June deadline show how enterprises actually adopt AI coding agents.

Article · 1mo ago0

Spec Kit Puts Specs Ahead of the Agent

GitHub's open toolkit turns intent into a living contract so coding agents stop freelancing your architecture.

Article · 1mo ago0

The Cost of the Compiler in the Age of AI

Scarf's migration from Haskell to Python reveals how agentic workflows are rewriting the rules of language selection.

Article · 1mo ago0

Why AI Editors Keep Generating Prototype Pollution Vulnerabilities

Recursive merge helpers generated by AI tools frequently lack basic security guards, exposing JavaScript applications to prototype pollution.

Article · 1mo ago0

GPT-5.6 Gets Smarter, and Harder to Trust

OpenAI's new flagship finds more bugs and takes more liberties, and the real productivity bottleneck still isn't the model.

Article · 1mo ago2

The cleanup bill for AI code is now itemized

A refactoring shop that bills by the line deleted is a market signal worth reading closely.

Article · 1mo ago5

Your AI velocity gauge reads backward

A controlled trial found experienced developers felt 20% faster with AI while the stopwatch clocked them 19% slower.

Article · 1mo ago2

The Vibe Coding Bill Comes Due

AI-generated code is breaking GitHub and degrading codebases. Automated quality gates are the only way to survive the flood.

Article · 2mos ago5

Ditching ANTLR: How PostHog Rebuilt Its SQL Parser for a 70x Speedup

Replacing a parser generator with a hand-rolled recursive-descent parser using AI agents, differential testing, and compiler design.

Article · 2mos ago3

GLM 5.2 Is a Point Behind Opus — Until the Task Runs for Hours

Open weights and a 5.7x price cut make the near-parity headline real, but the gap reopens exactly where long-horizon agents live.

Article · 2mos ago2

When to Reject AI Code Even If It Works

A practitioner's framework for maintaining code quality, ownership, and technical intuition in the age of generative agents.

Article · 2mos ago0

Cursor's $60B Sale Tests Whether a 'Neutral' AI Editor Can Stay Neutral

SpaceX folding the most popular AI code editor into Musk's model empire turns Cursor's biggest strength — its model-agnosticism — into its biggest open question.

News · 2mos ago5