Blog

Daily notes on AI, testing, and building software.

April 28, 2026AI/LLM Updates
How Claude Mythos Is Redefining Security Testing — And What QA Engineers Should Know
Anthropic's Claude Mythos Preview has autonomously discovered thousands of zero-day vulnerabilities across every major operating system and browser — including 271 in Firefox alone — without human guidance after the…
April 28, 2026AI/LLM Updates
GPT-5.5 Is Here: What It Means for the Future of Automated Testing
OpenAI's GPT-5.5, released on April 23, 2026, is explicitly optimized for writing and debugging code, operating software, and chaining tool calls until a task is complete — capabilities that put it squarely in the…
April 28, 2026AI/LLM Updates
GPT-5.5 Codex Is Here — and It's Rewriting the Rules of Automated Code Review
GPT-5.5 Codex, released on April 23rd 2026, achieved 79.2% accuracy on a curated code-review benchmark — a massive leap from the previous 58.3% — meaning AI-assisted code review is no longer a novelty but a credible…
April 28, 2026Test Automation
GPT-5.5 and the Rise of Autonomous QA Agents: A New Paradigm for Test Automation
OpenAI's GPT-5.5, released April 23, 2026, dramatically improves agentic task completion — writing code, operating software, and finishing multi-step workflows with minimal human input. For QA teams, this accelerates…
April 28, 2026AI/LLM Updates
GPT-5.5 Drops — And Its Agentic Coding Leap Has Big Implications for QA
OpenAI's GPT-5.5, released April 23–24 2026, is the most capable model yet for long-horizon coding tasks, real-world GitHub issue resolution, and multi-step agentic workflows — precisely the domains where automated test…
April 28, 2026AI/LLM Updates
GPT-5.5's Agentic Coding Leap: What an 82.7% Terminal-Bench Score Means for Test Automation
OpenAI's GPT-5.5 scored 82.7% on Terminal-Bench 2.0 and 58.6% on SWE-Bench Pro — benchmarks that directly simulate the multi-step, tool-using workflows that underpin modern test automation. When an AI model can plan,…
April 28, 2026Vulnerability Analysis
CVE-2026-1949: Delta Electronics AS320T Critical Stack Buffer Overflow — What It Is & How to Fix It
CVE-2026-1949 is a critical stack-based buffer overflow vulnerability (CVSS 9.8) in the Delta Electronics AS320T industrial AC servo drive, disclosed on April 24, 2026. An unauthenticated remote attacker can exploit the…
April 28, 2026Vulnerability Analysis
CVE-2024-27199: JetBrains TeamCity Authentication Bypass via Path Traversal — How to Detect, Fix & Harden Your CI/CD Pipeline
CVE-2024-27199 is an authentication bypass vulnerability in JetBrains TeamCity On-Premises, stemming from a path traversal flaw (CWE-22) in the server's web component. An unauthenticated remote attacker can exploit this…
April 28, 2026Test Automation
Claude Managed Agents: The Infrastructure Shift That Could Redefine QA Pipelines
Anthropic's Claude Managed Agents — now in public beta — give QA teams a fully managed, production-grade agent harness with built-in sandboxed execution, state management, and memory, eliminating the infrastructure…
April 28, 2026AI/LLM Updates
Anthropic's Claude Managed Agents Are Rewriting the QA Playbook
Anthropic's Claude Managed Agents — launched in public beta on April 8, 2026 — give QA teams a fully managed infrastructure for running autonomous, multi-step testing agents without managing servers, scaling, or…

Latest from the blog