howtonotcode.com

WINDSURF-EDITOR

APR_10 // 06:20

DX launches AI Code Insights to measure AI-generated code, agent effectiveness, and ROI across your org

DX released AI Code Insights to attribute AI-generated code, surface agent bottlenecks, and estimate ROI across IDEs and agents. DX’s new [AI Code In...

ANTHROPIC

APR_08 // 06:24

Claude Code 2.1.94 ships Bedrock (Mantle) support; 2.1.96 hotfixes Bedrock auth regression

Anthropic’s Claude Code added Amazon Bedrock (Mantle) support in 2.1.94 and fixed a Bedrock auth regression in 2.1.96 amid reliability debate. The [v...

CURSOR

MAR_30 // 06:19

AI coding agents in 2026: big capability jump, falling prices, and safety wrinkles

Agentic coding tools got powerful and cheaper in 2026, but stability and safety concerns still demand tight guardrails. A technical comparison finds ...

ANTHROPIC

MAR_26 // 07:17

Claude Code adds Auto Mode, desktop control, and enterprise safeguards; v2.1.84 ships PowerShell and ops hooks

Claude Code just grew up: auto-permission runs, Mac computer control, and enterprise guardrails landed alongside a Windows PowerShell tool and new ops...

WINDSURF

MAR_25 // 07:27

Choosing AI coding agents: Antigravity vs Windsurf for production refactors and rapid prototyping

Antigravity emphasizes parallel autonomous agents while Windsurf emphasizes reversible, human-reviewed flows, which pushes them toward different sweet...

ANTHROPIC

MAR_25 // 07:24

Claude Code’s new Auto Mode lands with real guardrails and team-friendly policy controls

Anthropic shipped Auto Mode for Claude Code plus enterprise-grade safety and policy features to let agents act with fewer prompts but tighter controls...

CLAUDE-CODE

MAR_11 // 07:24

New long-horizon benchmarks say coding agents regress under maintenance; treat them like junior devs with tougher CI

A new wave of long-horizon benchmarks shows most coding agents ship regressions over time, not just fixes. A summary in [TLDR Dev 2026-03-09](https:/...

MASSGEN

MAR_10 // 07:42

Agents ace one-shot coding, but most break your code over months—time to harden CI and adopt evaluator loops

New results say most coding agents cause regressions during long-term CI, and a new MassGen release adds built-in evaluator loops to catch issues earl...

SCALE-AI

MAR_09 // 07:25

SWE‑Atlas and SWE‑CI show AI coding agents still break real codebases

New agent benchmarks show LLM coders falter on real maintenance tasks and can quietly ship regressions. Scale AI’s new [SWE‑Atlas benchmark](https://...

CLAUDE-CODE

FEB_24 // 21:22

Pragmatic agentic coding workflow using Claude Code

A YouTube walkthrough shows a pragmatic agentic coding workflow to build software end-to-end with coding agents like Claude Code. This [walkthrough v...

PROJDEVBENCH

FEB_03 // 18:40

E2E coding agents: 27% pass, cheaper scaling, and safer adoption

A new end-to-end benchmark, [ProjDevBench](https://arxiv.org/html/2602.01655v1)[^1] with [code](https://github.com/zsworld6/projdevbench)[^2], reports...

GITHUB-COPILOT

JAN_23 // 07:49

Study: Where AI-authored PRs Fail—and How to Improve Merge Rates

A large study of 33k agent-authored GitHub pull requests across five coding agents finds that documentation, CI, and build-update PRs have the highest...