AWS Emulator is a downloadable tool for running and testing AWS applications locally, built entirely by autonomous AI agents without engineers writing or reviewing its code. It began as a weekend experiment after an engineer prompted Kiro to create tests from the AWS CLI, verify them against real AWS, and implement an in-memory service that passed those tests. A first version of SQS appeared quickly, but turning the experiment into a product required a system of constraints and quality checks rather than simply giving agents broad freedom.
The system divides work among three agent teams. Test-writing agents use AWS API models and the live cloud to create and verify real-world scenarios, which form a growing suite of tens of thousands of fidelity tests. Issue-finding agents run those tests against the emulator and group failures; fixing agents address individual issues. Each change must pass build, coding-standard, security, and regression checks before merging. Hundreds of agents can work concurrently, reportedly resolving thousands of issues per day, while failed checks send changes back for revision. The release process packages the emulator for download, and its code and tests are published on GitHub under a CC0 license, alongside records of fixed issues and outstanding gaps. The project’s central claim is that reliable autonomous software development depends on bounded tasks, explicit tests, and a rigorous merge gate; further details on fidelity, security, and the agent workflow are planned.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
A Hacker News poster asks which practical AI skills individuals can learn online to benefit economically from LLMs and agents. They want specific, hands-on recommendations suited to someone with a moderately technical background, without requiring a degree. (news.ycombinator.com)
Former OpenAI researcher Will Depue claims hidden initialization patterns in six Chinese open-weight AI models match Nvidia Blackwell hardware, including systems restricted from export to China. He says the matches were reproduced on real chips and independently checked by researchers, though the claims are based on his forensic analysis. (twitter.com)
Antithesis built a system that beats NetHack on nearly 80% of game seeds within five minutes, across character builds. Successful runs take a median of under two minutes, advancing the company’s goal of creating smarter fuzzers and autonomous systems. (antithesis.com)
OpenCyclone is a free, open-source Android agent that uses your existing apps to carry out tasks through a hidden screen. It asks for approval before actions like sending messages and lets users connect their own AI models. (opencyclone.vercel.app)
Sam Bankman-Fried’s $500 million investment gave Alameda nearly 14% of Anthropic, a stake that would be worth about $37 billion at the AI company’s expected $1.5 trillion IPO valuation. The stake was sold in bankruptcy to repay FTX customers and creditors after Bankman-Fried’s businesses collapsed. (ft.com)
llama.cpp and ggml have reached v1.0, establishing stable public C APIs and clear versioning rules for breaking changes. The release strengthens the foundation for running local, multimodal AI across a wide range of hardware. (huggingface.co)
Today's best Hacker News stories, summarized and screenshotted, one email a day.