#claude code
Claude Code: 30 AI articles covering claude code news, analysis, and research
Articles
Meet Anthropic's sandbox-runtime: OS-Level Sandboxing for AIβ8
Anthropic's sandbox-runtime (srt) is an open-source OS-level sandbox for AI agents that restricts file and network access without containers.
Vercel Open-Sources durable-harness for Crash-Proof Coding Agentsβ9
Vercel open-sources durable-harness, a package that keeps coding agent sessions alive through crashes and timeouts by logging each session durably.
AI Is Making Smart TVs 'Dumb' Again: Developers Use AI to Stripβ9
Developers are using AI to strip ads, bloatware, and tracking from smart TVs, restoring control and privacy to frustrated viewers tired of surveillance and forc...
What Claude Code Can and Can't Do with Full Access Inside aβ8
Docker Sandboxes lets Claude Code edit files and run tests autonomously in an isolated microVM. See what it can do, its limits, and how to set it up.
Together Link: A Free CLI That Runs Open Models Like Kimi K3 andβ9
Together Link is a free MIT-licensed CLI that connects Claude Code, Codex, and OpenCode to open models like Kimi K3 and GLM 5.3 hosted on Together AI.
How to Break the AI Coding Agent Fix Loopβ10
Why AI coding agents get stuck in fix loops and a five-step methodβstop, revert, restate, isolate, verifyβto break the cycle and ship working code.
Anthropic Launches Claude Code Projects in Beta: Parallel Cloudβ8
Anthropic's Claude Code Projects beta splits one conversation into parallel cloud sessions with branches, running tasks and pushing fixes even after you close y...
Stanford's Paper2Agent Turns Research Papers Into Reproducibleβ8
Stanford's Paper2Agent converts research papers and code into MCP servers, letting AI agents run methods via natural language to boost reproducibility.
Context Engineering Inside the Harness: 4 Mechanisms That Beatβ7
Long-horizon AI agents fail from context overflow and goal loss. Learn how compaction, memory, budgeting, and todo-state in the harness fix it.
Anthropic Adds Plugin Evals to Claude Code: 6 Grader Types, a Noβ7
Anthropic's `claude plugin eval` command for Claude Code runs plugin evals with six grader types, a no-plugin baseline, and a CI gate for skills.