VS Code 1.122: Offline AI Without GitHub Sign-In
VS Code 1.122 ships BYOK without GitHub auth, device emulation, and richer OTel signals. Here is what changed and how to set up ...
Statewright: State Machine Guardrails for AI Agents
Your AI coding agent is failing in production, and the model isn’t the problem. The ...
Claude Opus 4.8 in GitHub Copilot: Better Code Reasoning, Same Price
Claude Opus 4.8 is now in GitHub Copilot for Pro+, Business, and Enterprise users. Here's ...
EY Canada’s AI Report Had 59% Fake Citations. Now AI Repeats Them.
Three researchers found 16 of 27 EY Canada citations were fake. Worse: Claude, ChatGPT, and ...
Cursor 3.6 Auto-review: Fewer Prompts, Safer Agents
Cursor 3.6 ships Auto-review Run Mode: a classifier subagent that handles risky shell, MCP, and ...
Google ADK 2.0: Graph Workflows Ship, LangGraph Has a Fight
Google ADK 2.0 ships a graph-based workflow runtime at I/O 2026. Here’s what changed, the four breaking changes for 1.x users, and how ...
Docker Model Runner CVE-2026-5843: Two Flaws That Let a Bad Model Own Your Mac
Two high-severity CVEs in Docker Model Runner let any container execute code on your macOS ...
Mistral Vibe Is Here: Le Chat Becomes a Full Coding Agent
Mistral renamed Le Chat to Vibe on May 28 and shipped a coding agent with ...
Google Antigravity 2.0: CLI, SDK, and What Actually Shipped
Google Antigravity 2.0 launched at I/O 2026 with a desktop app, CLI (agy), SDK, and ...
Illinois SB315: America’s First AI Safety Audit Law for Developers
Illinois passed SB315, requiring annual third-party AI safety audits of frontier models. Here's what the ...