Model once, code a thousand times: the case for model-plus-code control flow
willcb · x · 2026-09-21
- Replying to tenobrus, willcb clarifies that the original argument favors Jev-style "model-plus-code" control flow for repetitive processes, not agent-plus-skill.
- Core point: if you need something done once, just point the "AGI token cannon" at it; if it runs 1000x a day, codify the flow in code instead of relying on prompting every time.
More from coding & agent
- Anthropic Engineer Shows How Top Users Run 100+ Self-Learning Claude Code Agents — goyalshaliniuk · 2026-09-21
- Your Agent Said "Done" — But What Actually Changed? A Control-Plane Design — GlenBradley · 2026-09-21
- pm-skills Hits 26.5k Stars: 69 PM Skills and 42 Workflows for Claude Code — tom_doerr · 2026-09-21
- Z.ai Open-Sources Its Coding Agent Workbench ZCode Under Apache 2.0 — cephaloform · 2026-09-21
- A new role emerges: 'vibecoder relations' as non-coders drive model launches — venturetwins · 2026-09-21
- 220K agent tool calls analyzed: model-watching-model Jev great at progress tracking, weak at security — hrishioa · 2026-09-21