AI CODING

Z.ai shipped GLM-5.2 in mid-June with a usable 1M-token context window, two thinking-effort levels, and MIT open weights now released. Here is the setup guide for Claude Code, pricing breakdown, and what to test before the benchmarks arrive.

Kimi K2.7-Code is Moonshot's open-source 1T parameter coding model with 30% fewer reasoning tokens than K2.6. Here's how to set it up with Claude Code, pricing breakdown, and honest benchmark analysis.

Kiro is AWS's new agentic IDE built on spec-driven development. Amazon Q Developer support ends April 2027. Here is what Kiro does differently and how to migrate.

Fable 5 lists at $10/$50 per million tokens - twice Opus 4.8. But list price is the wrong number. Here is the cost-per-outcome math that actually decides whether the upgrade pays.

Anthropic shipped Fable 5 and a June 22 subscription cliff. OpenAI shipped GPT-5.5 inside Codex plus automations, browser use, and computer control. Here is the honest June 2026 update on which tool fits which developer.

Fable 5 launched June 9 at 2x GPT-5.5's price with a 22-point SWE-Bench Pro gap. Here is the decision framework for choosing between them.

SWE-Bench has an 81% false-positive problem. FrontierCode replaces it with mergeability as the metric - and the scores are sobering for every AI coding tool on the market.

Running multiple Claude Code agents on the same repo causes branch collisions and stash chaos - git worktrees fix this by giving each agent its own isolated directory while sharing one Git history.

GitHub Copilot switched to AI Credits billing on June 1 - here is what the change means for your team's budget, how Copilot Max fits in, and how costs compare to Claude Code and Codex.

Microsoft unveiled seven in-house MAI models at Build 2026, including MAI-Code-1-Flash now shipping in GitHub Copilot. Here is what the MoE architecture, training data, and Copilot rollout mean for your team's toolchain decisions in H2 2026.

Windsurf is now Devin Desktop, owned by Cognition after a turbulent 2025 acquisition saga. If the ownership shuffle has you reconsidering your tooling, here is a step-by-step guide to moving your workflow to Claude Code.

A Hacker News thread on config files that run code points at the next AI coding risk: agent hooks, skills, and editor rules need review like executable dependencies.

OpenAI's harness engineering post and new token-use research point to the same lesson: agentic coding teams need token budgets, receipts, and eval loops, not vibes.

The rsync Claude debate shows why teams need reproducible defect forensics before AI attribution becomes a public blame machine.

Microsoft's new in-house coding model matters less as a benchmark headline and more as a signal that Copilot is becoming a routing layer for cost, latency, ownership, and review quality.

GitHub Trending is full of agent memory and context tools. The useful version is not magic recall. It is a context ledger: source-linked, scoped, expiring memory that agents can inspect and users can audit.

A huge Hacker News thread says domain expertise is the real moat in agentic coding. The sharper version: tacit judgment only compounds when you turn it into examples, tests, DSLs, and review gates.

The DevDigest blog is no longer just a folder of markdown files. It is becoming a small content operating system: posts, tags, RSS, search, llms.txt, route discovery, content expansion reports, and app-linked build logs.

The DevDigest tools directory is not just a list of links. One registry now feeds tool pages, category filters, comparison routes, RSS, JSON APIs, search, sitemap discovery, and content expansion loops.

The AI coding market is noisy. The changes that matter are easier to spot when you separate model capability, editor loops, terminal agents, background agents, agent frameworks, UI layers, context, security, and cost.