Claude API Tool Versions: response_inclusion Cuts Agent Bloat Now
Anthropic shipped web_search_20260318 and code_execution_20260521 on June 19. The new response_inclusion parameter drops consumed tool results from agent responses — here is how ...
Claude Platform WIF Is GA: Ditch the Static API Key Now
Last year, GitGuardian found 1.27 million AI-service credentials exposed on public GitHub — up 81% ...
Stack Overflow for Agents: AI Coding Memory Layer Lands
Stack Overflow launched an API corpus for AI agents June 10. It stops rediscovering solved ...
AutoJack: One Web Page Can RCE the Host Running Your AI Agent
Microsoft disclosed AutoJack on June 18: a 3-bug chain that lets a malicious web page ...
GLM-5.2 Hallucinates 3x Less Than GPT-5.5 — Open Weight Wins
Z.ai dropped GLM-5.2 under MIT license this week. It outperforms GPT-5.5 on coding while hallucinating ...
GitHub Copilot App Is Now GA: Run Multiple AI Agents in Parallel
GitHub Copilot App went GA on June 17. Here is what changes for your workflow: isolated worktrees, canvases, cloud automations, Agent Merge, and ...
AI Is Hunting Bugs Now: 2026 CVE Count Heading for 66,000
FIRST revised its 2026 CVE forecast to 66,000 — up 46% — as AI tools ...
Microsoft ACS: Open Standard for AI Agent Governance
Every team shipping AI agents in production is solving the same governance problem from scratch: ...
Amazon Bedrock AgentCore Memory: Build AI Agents That Remember
AgentCore Memory gives AI agents persistent memory across sessions. Learn the two-tier architecture, three extraction ...
GitHub Copilot Code Review Now Reads Your AGENTS.md
As of June 18, Copilot code review reads your AGENTS.md and uses it to shape ...