mariozechner.at
Mario Zechner · 5 korrents · 1 piece · mariozechner.at
Thoughts on slowing the fuck down5 korrents · 25 Mar 2026 · no page here yet
- A coding agent does not learn from its mistakes the way a person does -- it repeats the same error indefinitely unless a human notices and writes it down.
- The human bottleneck is a safety property: remove it and small, individually harmless coding errors compound at a rate nobody feels until it is too late.
- In an agent-written codebase the agent-written tests are equally untrustworthy; manually using the product is the only reliable measure of whether it works.
- Two people with agents can reach enterprise-grade codebase complexity in weeks -- what took organisations years, and they at least adapted to it as it grew.
- Agentic code search has recall that falls as a codebase grows, so the agent does not find the code it needs -- and which search tool you give it barely matters.