Dev to tackle a shelved 80-person-week task using mostly autonomous agentic AI
facontidavide · x · 2026-10-23
Developer facontidavide is starting next week a task estimated at 80 person-weeks of work that was never begun because of its size. He plans to complete it mostly with autonomous agentic AI and will report back the results — a public test of whether agents can compress large-scale engineering work by orders of magnitude.
More from coding & agent
- How to keep AI-built apps from looking vibe coded: designer themes plus a design MD file for agents — Roger_M_Taylor · 2026-10-23
- freeCodeCamp tutorial: how to build production-safe agent loops after a Claude Code run burned $50,000 — Roger_M_Taylor · 2026-10-23
- Sentry ships official MCP server letting AI assistants query errors, manage projects — modelcontextprotocol · 2026-10-23
- YouTube Trends MCP serves search interest and growth metrics to AI assistants — modelcontextprotocol · 2026-10-23
- Karpathy-inspired harness prompt turns Opus 5.5 into a self-verifying execution engine — Roger_M_Taylor · 2026-10-23
- GitHub moved 99.99999% of repos to Azure; per-reference quorums unlock agent-scale Git concurrency — marlene_zw · 2026-10-23