OpenSpec is a lightweight, open-source framework for creating and managing software specifications, allowing developers to capture requirements, validate them, and verify implementation matches. It supports over 265,000 developers per month and is integrated with various AI tools and platforms. OpenSpec creates a new spec every two seconds, with over 68,000 GitHub stars. AI summary
Firehose
Filtered to tagged “software development” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives
Browse by tag
artificial intelligence 89continual learning 27AI 23AI safety 13reinforcement learning 13agentic coding 12open-weight models 12AI agents 10machine learning 9AI ethics 8cybersecurity 8existential risk 8language models 8natural language processing 8ethics 7Reinforcement learning 6Diffusion models 5large language models 5multi-agent systems 5open-source 5recursive self-improvement 5robotics 5security 5software development 5Agentic AI 4artificial general intelligence 4mathematics 4Recursive self-improvement 4agents 3AI infrastructure 3
The cost of writing code collapsed, and the cost of reviewing, fixing and operating it is following, and I'm assuming it gets there. What's left of making software is finding out what people actually want, defining it precisely, and making …
For a while, I must admit, it looked as if software developer roles like mine were done for. How could we fight against tireless robots? But our industry is slowly realizing that making truly cutting-edge software still requires humans to t…
Before co-founding Kepler, Vinoo Ganesh led Spark at Palantir and built Project Frontline — a pioneering program for Forward Deployed Engineers. He takes us through the best practices of FDEs.
To build an AI software factory, you need to create a system with five stages: intake, isolation, verification, merge gate, and tool layer. The tool layer is the most decisive stage, where you integrate your model with your test runner, telemetry, feature flags, and deploy tooling to create a colleague, not just an autocomplete. A software factory should be a monorepo to live in one place and provide context to your agents, and verification should focus on precision rather than volume, using gates that ask if a comment is worth a human's time. AI summary