testing

This article recommends the Samsung Galaxy A17 5G and Galaxy A56 5G as representative low- and mid-tier Android devices for real-world web performance testing in 2026, based on market data and performance considerations.

A developer created a starter kit and evaluation suite for Vapi-based AI receptionists after discovering silent mis-booking errors, sharing the tool to help others catch similar issues.

Anthropic's always-on agent experiment Conway is ending its testing phase on July 24th, suggesting either a shutdown or a wider rollout to Max subscribers soon, which will indicate whether the company favors local or cloud-based persistent agents.

Niall Dabit explains a mental model for cloud agents as infinitely cloned laptop environments accessible via HTTP, and describes an experiment using a fork of Hermes Agent with DevinAI for automated fork maintenance.

A creator tests new AI models by challenging them to generate an animated SVG of a flamingo moonwalking on a Sardinian beach.

At the AI Engineer World's Fair, Phil Schmid gave a talk on why vibe-checking agent skills break in production and how to build reliable automated evals using negative test cases, skill limits, and ablation tests.

Discusses best practices for testing AI agents before deploying them to production environments.

Tested the new Qwen 3.8 model, a large language model with 2.4 trillion parameters.

oqoqo is a tool for building evals and custom benchmarks for real-world tasks.

An interview-based study across nine companies in six countries examining current autonomous driving system testing practices, challenges, and future trends, proposing an evidence-centered closed-loop testing framework.

Schema is a harness that enables frontier AI models to achieve 99% on the ARC-AGI-3 benchmark by having them write executable programs to model game environments, test predictions, and plan.

Libretto PR agents automatically investigate and fix failing Playwright scripts by opening GitHub pull requests with proposed code fixes.

Testing Freebuff, a free CLI agent designed to help cut development costs.

This article demonstrates how to detect full table scans in SQLite using its statement statistics API, and suggests integrating this into Rails to warn or raise in test/development environments.

Discusses how integrating tools like API Doctor, Socket, Semgrep, CodeRabbit, Postman, Playwright, GitHub Actions, Sentry, and PostHog can give AI coding agents senior-level instincts for code quality, security, and monitoring, shifting focus from speed to quality.

The author shares experiences testing humanoid robots and interviewing the people racing to build them, inviting questions in an AMA format.

A tweet recommending 10 standout skills from the UI Skills platform, including design engineering, animation, accessibility, and various front-end tools, with a detailed deep-dive into the 'emil-design-eng' skill.

This article discusses the insufficient testing of AI coding agents, highlighting a critical gap in ensuring their reliability and safety in software development.

KDE Linux has integrated openQA for end-to-end automated testing of its system images, replacing rudimentary tests with VM-based install and upgrade verification using Selenium via AT-SPI.

This paper discusses testing methodologies for financial controls in ERP data provisioning, likely aimed at improving audit and compliance processes.