Anyone actually running a dark factory for code? Spec in, PRs out
Summary
A discussion about whether anyone is operating a fully automated 'dark factory' for code, where specifications are input and pull requests are output, likely involving AI-driven development pipelines.
Similar Articles
Is anyone actually running coding agents autonomously from issue to PR?
A discussion inquiring about the real-world use of fully autonomous coding agents that take an issue and produce a PR without human steering, focusing on verification and manual oversight.
@RoundtableSpace: GITHUB JUST OPEN SOURCED A SYSTEM THAT FORCES AI AGENTS TO WRITE FULL SPECS BEFORE CODING 95K STARS IN DAYS
GitHub open-sourced a system that forces AI agents to write full specifications before coding, quickly garnering 95,000 stars.
I built an AI agent that goes from spec to shipped software - full pipeline demo
The author demonstrates JackHamr, a platform where autonomous AI agents build a dark-mode toggle feature from spec to deployment, with approval gates and sub-agent tasks.
I keep abandoning multi-agent setups because I can't verify the code they ship. How are you handling this?
A developer shares their frustration with multi-agent coding setups where verifying the output of parallel PRs is impractical, and describes building an AI QA agent that uses a real browser (via Browserbase) to automatically click through preview deploys and fail PRs that don't work as expected.
@danshipper: GitHub has a front-row seat to how code is changing now that everyone—and their army of agents—can ship code. In March …
GitHub COO Kyle Daigle discusses the surge in AI agent-created pull requests (17 million in March) and the projected 14 billion commits this year, emphasizing open-source maintainer control, usage-based pricing over per-seat licensing, and the collapsing developer/non-developer distinction as AI tools enable non-developers to build apps.