A full-autonomy build says models can now assemble entire systems from scratch
MoonL88537 · x · 2026-07-23
The author says the entire system is being built by models from the ground up, with the human only steering high-level decisions and architecture.
They describe the setup as a full-autonomy experiment and say models are already surprisingly capable, while extra components like classifiers are what tend to break the workflow.
Related event: Fully Autonomous Multi-Agent Experiment Goes Awry(4 posts)→
More from coding & agent
- Full course shows how to build agent graphs for parallel research and review — gerardsans · 2026-07-23
- Arcade CEO says enterprise agents are bottlenecked by permissions, not intelligence — kimmonismus · 2026-07-23
- Agents are now helping apps write better copy, not just generate code — JordanMorgan10 · 2026-07-23
- A browser tool built with Claude Code tracks property lines across drone footage — Vjeux · 2026-07-23
- Hermes merges 114 PRs, adding multi-window desktop support and tighter MCP handling — Teknium · 2026-07-23
- Patrick Debois says AI teams should fix workflow, not just buy bigger models — rohansrma1 · 2026-07-23