Development

Together Link connects coding agents to hosted open models. Learn how to trial it safely, check routing, and measure cost per accepted change.

Vinext 1.0 moves Next.js apps onto Vite with broader router support and cache warming—test compatibility before treating portability as a drop-in guarantee.

Tobias Lütke’s walgit puts a write-ahead log in object storage and makes every Git server a disposable cache — an open-source answer to Cursor’s Continuity.

GitHub’s stacked pull requests exit preview, splitting large changes into reviewable layers merged in one click.

MCP’s 2026-07-28 spec removes sessions and the initialize handshake, making the protocol stateless — here’s what changed and why it matters.

New quantization techniques enable running large language models locally with minimal quality loss, reshaping AI infrastructure and deployment economics.

Zero-day web framework vulnerabilities expose how slow coordinated patching can be—and why defense-in-depth matters more than fast patching alone.

GitHub Copilot and a new wave of AI tools are turning code review from a scarce bottleneck into a scalable quality gate for every pull request.

Multi-agent LLM systems are shifting from experimental chat interfaces to autonomous production systems.

Anthropic released an open-source framework for automated vulnerability discovery powered by AI.

Anthropic’s latest Claude breakthrough lets developers inject task-specific knowledge directly into prompts without fine-tuning, fundamentally shifting how we

AI models can now generate tests, find edge cases, and validate behavior at scale. But blindly using AI for testing creates false confidence.