Skip to content

Technical Blog

Blog

Expert tutorials & guides for modern developers

685 posts · Page 1 of 58

Sort by

Security & PrivacyOctober 13, 202620 min
Claude Code Hook Failures: onFailure Block Tested
Claude Code hooks fail open on most events. I tested onFailure block across four builds with cases like missing scripts, exit 1, timeouts and schema errors.
AI & Machine LearningOctober 13, 202618 min
OpenAI Dots: What Always-On Agents Mean for Teams
OpenAI's dots are always-on ChatGPT agents with their own cloud computer. What Business Premium buyers get, what it costs and what the Enterprise beta lacks.
AI & Machine LearningOctober 12, 202616 min
AI Agents Are Getting Work Email: What to Decide
Google's Gemini agent and Microsoft's autopilots can give AI agents their own work email and identity. Five decisions to make before you say yes to one.
AI & Machine LearningOctober 12, 202624 min
OpenAI Agents SDK maxTurns After Approval, Tested
I ran @openai/agents 0.19.0 and 0.20.0 side by side. In 0.20.0 the model call after an approval counts toward maxTurns, so a resume at maxTurns 1 can now throw.
Tooling & ProductivityOctober 9, 202635 min
Claude Code Mods: 10 Tested Use Cases (2026)
Claude Code mods explained with 10 tested use cases: guard risky commands, mask secrets, add commands, panes and tools. Every example passes claude plugin test.
AI & Machine LearningOctober 9, 202617 min
OpenAI Agents SDK 0.23: Tool Error Redaction Tested
I ran openai-agents 0.22.3 and 0.23.1 with a scripted model. The default tool error message no longer sends exception text to the model or to trace spans.
AI & Machine LearningOctober 9, 202613 min
Rogue AI Agents Hit Wikimedia: Lessons for Leaders
Wikimedia says suspected OpenAI agents edited its wikis, probed its tools and sent heavy traffic. What leaders who run agents or websites should do now.
Security & PrivacyOctober 8, 202621 min
ADK ToolCallIntegrityPlugin: Tamper Test Results
I rewrote an approved tool call in Google ADK TypeScript 2.2.1. It ran with no plugin and was blocked by ToolCallIntegrityPlugin, except in one setting.
AI & Machine LearningOctober 8, 202617 min
Personal Agent Protocol: What Businesses Should Do
Sierra and Meta's Personal Agent Protocol proposes how customers' AI agents sign in and act at your business. What it covers, what's missing, what to do now.
AI & Machine LearningOctober 7, 202615 min
AI Decision Models: Jev, Laya, Clef and More
Jev, Laya, Clef, Liquid d1 and more: what AI decision models are, what the benchmarks really show, where to download them, and use cases for every team.
AI & Machine LearningOctober 7, 20269 min
JEPA and World Models: A Hype Check for Leaders
JEPA and world models are a hot AI buzzword right now. What they are, what has actually shipped, and what leaders should and should not do about it yet.
AI & Machine LearningOctober 7, 202613 min
OpenAI Agents SDK needsApproval: Null Bug Tested
I ran OpenAI Agents JS 0.18.0 and 0.19.0 side by side. needsApproval got null for omitted optional fields until 0.19.0, and resumed runs now re-check it.