QA tester

Every story that matters to a QA tester, with one sentence on what it concretely means for them. 34 stories, latest first.

Oct 2026

Oct 19, 2026Harvard study of 718 firms: AI produces more code but does not speed up deliveryWith the increased volume of code, test automation and risk-based testing gain priority.Oct 19, 2026Blacksmith, an AI code-testing startup, reaches $1 billion valuationTesting and CI capacity are the bottleneck, so automation skills are becoming more valuable.Oct 13, 2026AI wrote the trading bot? Working code can still trade by the wrong rulesWorking code is not the same as a correct business rule; test it against the requirements.Oct 12, 2026Epic used vibe coding to build its new Epic Games LauncherWith fast, AI-driven releases, expand regression and performance testing.Oct 12, 2026Quality debt: AI-accelerated development brings production outages and testing gapsWith the flood of AI-driven changes, risk-based, automated and exploratory testing gain value.Oct 12, 2026Google AI Studio lets users build Android apps without code, from age 18 and without a developer accountExpect vibe-coded apps to spread, and to appear without having been tested.Oct 7, 2026Survey: AI-generated code shifts the bottleneck to debugging, slowing releasesTesting and debugging may face a heavier load, so capacity should be planned in advance.Oct 6, 2026Codex Auto-review goes free for ChatGPT users as GitHub changes Copilot review billing and Anthropic opens Claude Code Review betaAutomated review can be used to pre-screen pull requests, but it does not replace your own checks.Oct 6, 2026Meta study: two AI coding agents catch more bugs than one with a larger budgetCode should be checked by several independent agents rather than a single one.Oct 5, 2026GitHub launches ReviewBench, an open benchmark for AI code reviewThe benchmark helps evaluate how well AI reviewers detect defects.Oct 5, 2026Qodo 3.0 brings enterprise quality control to agentic software developmentA new enterprise tool is available for automatically checking AI-written code.Oct 1, 2026GitHub Copilot can now work with desktop apps through computer useTry it for UI testing of desktop applications, but check its reliability.

September 2026

Sep 28, 2026AI coding imposes a 'quality tax' on bank testingPrepare for a heavier testing load and for targeted regression checks of AI-generated changes.Sep 24, 2026GitHub Security Lab automates fuzzing with an AI agent frameworkAutomated fuzzing can complement the testing strategy.Sep 23, 2026Hungarian firm ITware develops AI-based software testing tool with HUF 201.8 million in EU fundingHungarian-developed AI test automation is coming; its features are worth following.Sep 22, 2026HWSW: Microsoft code quality at a low point, no evidence AI optimisation is to blameThe wave of bug fixes shows the importance of regression testing.Sep 21, 2026After AI code generation, verification is the bottleneck: more commits, not proportionally more releasesValidation gains in value, and testing and checking AI code become a central task.Sep 15, 2026Harness report: AI speeds up development, but deployment failure rate is 69%With more code being produced, test coverage and regression filtering are critical.Sep 14, 2026Czech analyses: LLM-generated code has been equally flawed for four years, only the volume is growingSecurity testing needs to be extended to AI-generated changes.Sep 14, 2026Anthropic describes how agentic coding strains CI and how it scaled test impact analysisRunning only the affected tests, rather than the full suite, can be the solution.Sep 11, 2026Anthropic adds plugin evals to Claude Code with six grader types, a no-plugin baseline and a CI gateEvaluation tests can be written for the agent's behavior.Sep 10, 2026TestMu AI adds mobile automation to Kane CLI with natural-language testsMobile tests can be written in natural language, but reproducibility must be checked.Sep 8, 2026AI speeds up software development, but the bottleneck shifts to review and operationsThe larger volume of changes puts more testing load on QA.Sep 8, 2026AI broke code review: experts disagree on what should replace itAutomated test coverage becomes the main line of defense against AI-generated changes.Sep 2, 2026MIT study: AI coding tools produce more code, but not more releasesMore generated code means more verification work, so prioritize test automation.

August 2026

Aug 25, 2026Research: more AI agents are reviewing other AI agents' code on GitHubDo not rely on AI review alone; build an independent testing layer.Aug 25, 2026Samsung sees Claude Code speeding up chip design but warns of serious errorsThe agent's output must be validated with domain-specific tests.Aug 18, 2026Asana replaces a legacy test system in two weeks with Codex, at about $12,000Test-system migration can be accelerated with agents, but coverage and correctness must be confirmed by human review.Aug 17, 2026Articles urge risk-tiered rules as AI-generated code review burden growsTests and acceptance criteria will play a more prominent role in verifying AI-generated code.Aug 10, 2026AI coding boom shifts software companies' focus to testing and verificationThe value of testing is rising, so build your skills towards automation and verification of AI-written code.Aug 10, 2026Weekly agent roundup: Cursor reportedly building 'Sand', Claude Code learns to launch a simulatorLook at how an agent that launches the simulator on its own could be used to automate mobile and UI testing.Aug 6, 2026Microsoft releases open-source unit test agent for Copilot CLI and VS CodeValidate agent-generated tests with mutation or coverage checks before trusting them.Aug 4, 2026Agentic AI rewrites code review economics as Rootly drops its small-PR ruleReviews can rely on automated evidence (tests, checks) instead of line-by-line reading.Aug 3, 2026Three in four AI-generated vulnerability patches break something; Veracode measures 44%Targeted regression tests are needed around security fixes.

↑