Rethinking Duplication and Validation in the Agentic Era
davidcrawshaw · x · 2026-07-12
This response builds on the vision of "agents writing code while humans read it," arguing that many static designs are merely "half-baked" because validation used to be too expensive. In the agentic era, as validation costs drop, many static constraints can be abandoned.
The author further points out that when agents continuously read and sync with the codebase, duplication and replication aren't necessarily bad things; instead, they could become an engineering paradigm better suited for collaboration.
Related event: Rethinking Programming Languages for the Agent Era(4 posts)→
More from coding & agent
- Resin lets an agent build standalone LLM inference engines; vLLM and SGLang optimize DeepSeek kernels differently — AccBalanced · 2026-10-27
- How I let my cloud Grok Bot code on my Mac mini via Tailscale, no public ports — talkaboutdesign · 2026-10-27
- Context layout is a cost decision: one memory edit can bust your entire agent prompt cache — dscape · 2026-10-27
- Alchemy adds effect/Workflow support across Durable Objects, Workflows and Lambda Durable Functions — samgoodwin89 · 2026-10-27
- Alchemy's Lambda Web Functions run plain Node web servers on Lambda, no OpenNext needed — samgoodwin89 · 2026-10-27
- Alchemy makes all ~2,850 AWS bindings work from any cloud, not just S3/Lambda/DynamoDB — samgoodwin89 · 2026-10-27