I think conventional accessibility testing methods are no longer sufficient for testing AI-native applications.

To determine the causal effect of a decision or tool, companies routinely use A/B testing: comparing outcomes reveals whether ...

We tested Perplexity’s Comet AI browser. Here’s what it gets right, where it falls short, and why its $200 price tag may ...

Three librarian judges rated each AI response on a 10-point scale. The test questions were designed to probe known AI blind spots, and covered five thematic categories. Most of th ...