AIDLC-WORKFLOWS is a harness-neutral toolkit that turns conversational AI coding assistants into structured, auditable software-delivery workflows. It provides a single core engine that runs natively across multiple runtimes - Claude Code, Kiro (IDE and CLI), Codex CLI, Cursor, opencode, and GitHub Copilot - plus harness-specific manifests and plugins. Installation is automated via platform installers or a manual Bun-based runtime, and projects are configured by selecting a harness and provider. Workflows are invoked through a simple prompt (for example, /aidlc Build a REST API...), after which the system selects a workflow, solicits missing decisions, and pauses at human approval gates. The repository includes quick-start instructions, harness guides, and troubleshooting steps to resolve common runtime and PATH issues.
The methodology enforces lifecycle discipline: five phases and 33 stages, 14 named agents (11 domain experts, two reviewers, and an adaptive composer), 11 workflow profiles for different work types, human approval gates, and a 119-event audit trail with persistent state and learned steering rules. Core, harness, plugins, tools, docs, tests, and packaging are neatly separated so contributors edit core or harness code rather than generated outputs. Recommended models and effort settings are documented (Claude Opus 4.8 recommended), and the project warns that generative AI can err, so generated output and costs require human review. Development commands, packaging scripts, and test suites are provided for deterministic builds and release workflows.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
ChatGPT became widely used among students for solving problem sets, shifting academic dynamics. The physicist initially dismissed AI but later witnessed its growing influence in education and research. (thetheorygirlie.substack.com)
Felix Rieseberg discusses how to be more ambitious with AI by focusing on speed, altitude, depth, and range in tasks. He emphasizes raising abstraction levels and integrating knowledge across fields to unlock greater potential with AI tools like Claude. (felixrieseberg.com)
Geoffrey Hinton warns that AI development is creating alien-like beings and humanity has only a few years to adapt. He criticizes Donald Trump's understanding of superintelligence and emphasizes the need to prioritize human interests in AI progress. (theguardian.com)
Hardwired converts JavaScript code into a neural network that runs in a browser without GPU, with no training needed. It allows for real-time weight adjustments and complex tasks like search and parsing using WebGPU kernels. (chenglou.me)
Next-Concept Modeling (NCM) is a two-stage, coarse-to-fine framework that generates text faster and with better quality than existing diffusion language models. It uses hierarchical encoding and parallel prediction to outperform benchmarks in speed and accuracy across various tasks. (arxiv.org)
AI safety concerns are shared by independent researchers and industry leaders alike, contradicting conspiracy theories that companies exaggerate dangers for profit. Prominent AI scientists have voiced serious warnings about existential risks, regardless of corporate affiliation. (astralcodexten.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.