Topic

#Ai Coding Agents

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

Article 1w ago 7

Google's Conductor Now Plugs Into Claude Code

The spec-driven Gemini CLI extension is reborn as a portable plugin for Antigravity CLI and Anthropic's agent.

Lenn Voss

awesome-design-md is scaffolding, not a design system

The 112k-star pile of borrowed brand tokens pays off once you lint it and rewrite it as your own.

Article · 1w ago7

The Agent Harness Is the New Web Framework

Coding agents from every vendor converged on the same eight primitives, and that layer is now commoditizing.

Article · 3w ago6

ProofRun Wants Receipts for Your Coding Agent's Claims

A tiny Go tool treats agent test claims as cache entries that expire — and previews where agent trust is heading.

Article · 3w ago5

AI Broke Half the Case Against Formal Verification

The 1979 objections are collapsing on proof labor and hardening on specifications, exactly where developers now need judgement.

Article · 3w ago0

The Real Cost of AI-Porting 250k Lines of Fortran

An agent moved Nagoya's 27-year-old typhoon simulator to GPUs, and the validation harness did the heavy lifting.

Article · 4w ago0

What a 232x AI Kernel Speedup Actually Proves

A GPU MODE contestant ran Codex in day-long optimization loops. The harness matters more than the multiplier.

Article · 4w ago0

Claude Code's New Session Guide Is Really About the Meter

Anthropic's candid efficiency tips double as an admission: agent tooling still makes you manage its cache by hand.

Article · 4w ago5

When the Spec Becomes the Code Review

A solo developer's $2,430 refactor of 189 files probes agentic coding's blind spot: changes with no test oracle.

Article · 4w ago1

There Is No Best Language for Coding Agents

Dan Luu's large-scale evals show the token-efficiency case for terse languages collapses on real tasks.

Article · 1mo ago2

Ante Bets Coding Agents Should Be Single Binaries

A 15MB Rust agent with llama.cpp baked in gets the architecture right and the trust model wrong.

Article · 1mo ago3

OpenChamber Bets Your Coding Agent Doesn't Need a Terminal

The MIT-licensed opencode frontend signals the real fight in AI coding: the supervision layer, not the harness.

Article · 1mo ago5

Benchmark Cursor, Aider, and Claude Code on Your Own Repo

Build a headless harness that scores AI coding agents on real issues from your codebase.

Tutorial · 1mo ago0

Meta and AWS Just Agreed on How AI Agents Should Code

Muse Code and Kiro Crew launched a day apart — and converged on the same parallel-agent architecture.

Article · 1mo ago0

Meta's Muse Code Is a Data Play Dressed as a Coding Agent

The agent trails Claude Code on Meta's own benchmarks, but the contributor tier's 90% discount is the real product.

Article · 1mo ago0

Meta Just Put a Sticker Price on Your Codebase

Muse Code's 21x contributor discount is the first explicit per-token market rate for training rights on developer data.

Article · 1mo ago0