AI Briefing#software-testing
The latest AI and developer news about #software-testing, with the original source and a short summary.
The latest AI and developer news about #software-testing, with the original source and a short summary.
The experiment cost $840 in API fees, with a rough estimate that human time per bug dropped from two days to a few hours.
The report details the production of machine-checked proofs for 239 entry points across 123 libraries, identifying bugs that survived extensive fuzzing.
The system achieved a 60% true-positive rate and engaged 589 engineers through a human-on-the-loop workflow.
The startup leverages the model's computer use capabilities to simulate user interactions and detect UI bugs that static code review misses.
The feature allows agents to operate desktop applications to verify the functionality of the code they generate.
AIPass implemented mutation-based and side-effect checkers that analyze test behavior rather than string content, reducing flagged lines by roughly half in initial audits.
Analysis of 14 sessions by AI agents in a large open-source monorepo revealed that 33% of modified source files were not included in the import closure of the tests that were executed.
Cognition has integrated GPT-6 Astra to strengthen Devin's self-testing and verification capabilities.
The Service Web Development Team combined ATDD and AI agents to preemptively block 1,717 defects before QA began.
Deltix, an AI agent-based tool that performs mobile app testing using natural language, has been released.
An AI agent automatically tested COBOL-to-Java conversion results to increase code path coverage.
AWS DevOps Agent has released a Release Management feature in preview that reviews and tests code changes.
This proposes a testing methodology in which AI agents design and execute tests to validate claims made by distributed and stateful systems.
ElevenLabs has launched a testing feature that can verify agent performance and reliability at scale.
An AI QA tool that generates analysis reports by letting you ask questions about Playwright test data in natural language.
It provides a key checklist of steps to take before building evaluation infrastructure in order to successfully build AI agents.
LLMs generate tests on the fly to catch regression bugs right after code changes.
Testing lowers business risk by reducing regression bugs and mismatches with requirements.
Kakao has developed an AI QA agent that autonomously executes natural language test cases by leveraging LLMs and accessibility APIs on its DeviceFarm infrastructure.
A newly onboarded QA engineer with a background as an iOS developer shares the 5-month growth and onboarding experience at Oliveyoung.
By automating 308 tests across 4 platform combinations, the time was reduced from 102 hours to 7 hours.
QA creates core value by minimizing product defects and helping facilitate smooth communication between developers and users.
A proposal has been presented for using generative AI to automate the QA process from requirements analysis to defect analysis, boosting efficiency.
To overcome the limits of complex object-based data setup, this article proposes an efficient way to manage test data using JSON files.