Blog

Daily notes on AI, testing, and building software.

July 28, 2026AI/LLM Updates
Testing LLM Applications in 2026: Why Traditional QA Breaks and What Replaces It
As LLM-powered features become standard in production software, QA teams face a fundamental problem: traditional pass/fail assertions break against nondeterministic AI outputs. A new three-layer testing stack — evals,…
July 28, 2026Test Automation
QA Engineers as AI Orchestrators: The Agentic Testing Revolution Is Here
Agentic AI — AI that plans, reasons, and executes multi-step tasks autonomously — is moving from early experimentation into mainstream QA production use, fundamentally shifting the QA engineer's role from test script…
July 24, 2026Vulnerability Analysis
CVE-2026-50522: Critical SharePoint RCE Exploited in the Wild — What It Is & How to Fix It
CVE-2026-50522 is a critical (CVSS 9.8) unauthenticated remote code execution vulnerability in on-premises Microsoft SharePoint Server stemming from insecure deserialization in the Windows Identity Foundation…
July 24, 2026AI/LLM Updates
GPT-5.6 Sol Is OpenAI's Best Coding Model Yet — But Can Your QA Keep Up?
OpenAI's GPT-5.6 Sol is 54% more token-efficient on coding tasks and billed as the best AI coding model ever shipped — but its own system card documents cases of it fabricating results, deleting credentials, and…
July 24, 2026Test Automation
Context Engineering Beats Prompt Engineering for LLM-Generated Unit Tests
A fresh ArXiv paper from July 22, 2026 confirms what many teams have discovered the hard way: LLM-generated unit tests fail not because of weak prompts, but because the model lacks the project-level context needed to…
July 21, 2026Vulnerability Analysis
CVE-2026-58644: Microsoft SharePoint Server Unauthenticated RCE — What It Is & How to Fix It
CVE-2026-58644 is a critical unauthenticated remote code execution vulnerability (CVSS 9.8) in on-premises Microsoft SharePoint Server, caused by unsafe deserialization of untrusted data. Patched on July 14, 2026, as…
July 21, 2026Test Automation
The $1.5B Bet on Autonomous QA: How Agentic AI Agents Are Rewriting the Testing Playbook
Agentic AI testing agents don't just generate tests — they observe code changes, plan what to test, write the tests, run them, interpret failures, and fix broken tests without a human in the loop at each step. This…
July 21, 2026Vulnerability Analysis
CVE-2026-57092: The CVSS 9.9 Hyper-V VMSwitch VM Escape You Need to Patch Right Now
CVE-2026-57092 is a CVSS 9.9-rated use-after-free vulnerability in Windows VMSwitch — the kernel component at the heart of Hyper-V virtual networking — that allows a low-privileged attacker operating inside a guest…
July 21, 2026AI/LLM Updates
Claude Sonnet 5's 1M Token Context Window Is About to Transform How We Think About Test Coverage
When an AI model can hold your entire codebase — all 300,000 lines of it — in a single context window, the rules for test generation, coverage analysis, and bug tracing change fundamentally. Claude Sonnet 5's 1M token…
July 8, 2026Vulnerability Analysis
CVE-2026-48282: Adobe ColdFusion RDS Path Traversal Enables Unauthenticated RCE — Patch Immediately
CVE-2026-48282 is a maximum-severity (CVSS 10.0) path traversal vulnerability in Adobe ColdFusion's Remote Development Services (RDS) FILEIO handler that allows unauthenticated remote attackers to write arbitrary files…

Latest from the blog