Curated reads on AI agents, credentials, and the auth ecosystem. The trends, takes, and breakdowns we are watching across the agent space.
ChatGPhish: every page your agent summarizes is now a phishing surface.
Permiso disclosed three working prompt-injection chains in ChatGPT's Markdown renderer on May 29, 2026: fake OpenAI security buttons, inline QR codes that pivot to mobile, and tracking pixels that leak IP and User-Agent. Why the renderer is the wrong trust boundary, and what every browse-with-LLM product just inherited.
Claude Opus 4.8 ships 1,000-subagent Dynamic Workflows. Now multiply your blast radius..
Anthropic released Claude Opus 4.8 on May 28, 2026 with Dynamic Workflows, letting Claude Code orchestrate up to 1,000 subagents per run. Here is what the release actually changes, and the credential-management problem nobody is talking about.
GitHub Copilot just became a meter: what the AI Credits shift means for coding agents.
On June 1, 2026, GitHub Copilot replaced premium requests with metered AI Credits priced at API rates. Here is the SKU shift, the dev backlash, and what per-token billing changes for teams running coding agents at scale.
OpenAI frontier models and Codex land on AWS Bedrock: what changes for agent builders.
OpenAI's GPT-5.5, GPT-5.4, and Codex went GA on Amazon Bedrock on June 1, 2026. Here is what is actually in the box, how access works, and what it means for how you handle credentials.
