How Duolingo Used LLMs to Automate iOS Unit Test Generation at Scale
DuolingoRelated reading
hogbaysoftware.com9d agoLLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks. However, existing safety testing targets expert-designed safety violations, and the corresponding outcomes are evaluated by hard-coded
Shared by @ai-firehose.column.social ↗
arxiv.org11d ago
Duolingo Blog20d ago
You just merged an AI-assisted feature branch, the code review looks clean, and the app works in your...
dev.to·Tech by Flipboard·1mo ago·8 min readDocket runs AI-driven end-to-end tests across web, iOS, Android, and desktop, using coordinate-based automation and self-healing steps to reduce flaky test maintenance.
Product Hunt — The best new products, every day·2mo ago·1 min read
github.com3mo ago
Product Hunt3mo agoGolden sets are unit tests for probabilistic behavior: curated cases, versioned rubrics, and gates that prevent quality regressions from shipping as surprises.
heavythoughtcloud.com4mo ago
news.ycombinator.com4mo ago
Product Hunt4mo ago
testflows.com4mo ago
Product Hunt5mo ago
morphllm.com5mo ago
Product Hunt6mo ago
keelcode.dev6mo ago
CSS Author
