Reins Engineering

Hurl Stops Vibe Coding Drift

Hurl Stops Vibe Coding Drift

Vibe coding collapses into logic drift within three months. CMU, METR, DORA, and Amazon prove it. Declare API contracts in plain text with Hurl and lock them with a ratchet — drift is structurally suppressed without constraining the AI's freedom.

Ratchet Code That Exploits IFEval

Ratchet Code That Exploits IFEval

LLM sycophancy bias is not a bug but an asset. Combine the instruction-following ability that IFEval measures with deterministic feedback, and even a 4.5B local model produces a convergence loop that generates correct code.

yongol — The Keel of AI-Coded SaaS

yongol — The Keel of AI-Coded SaaS

Vibe coding collapses at 200 endpoints because AI cannot distinguish decisions from implementation details. yongol shifts the AI workload from code to 10 declarative specs and enforces cross-layer consistency before compilation. Harness with reins.

AI Sycophancy Bias Is a Business Feature

AI Sycophancy Bias Is a Business Feature

LLM sycophancy is not a bug. It is a mathematical inevitability of RLHF and a commercial feature that big tech has no incentive to fix. This is why LLM-as-Judge is structurally impossible.

Why Coding Agents Work and Why They Break

Why Coding Agents Work and Why They Break

The same model hallucinates in web chat yet ships 200-line features in a coding agent. It is not the model that changed -- it is the topology. Generation can be probabilistic. Verification must be deterministic.

Ratchet Pattern — How to Make an Agent Finish the Job

Ratchet Pattern — How to Make an Agent Finish the Job

I asked an AI agent to write tests for 527 functions. It stopped at 40 and declared 'done.' The Ratchet Pattern forces completion by delegating the done/not-done decision to a mechanical verifier — so the agent keeps going until the machine says stop.

Feedback Topology Over Model IQ

Feedback Topology Over Model IQ

The same model stalls at 40 or completes all 527. The difference is not the model — it is the feedback structure. LLM performance depends far more on how fast and deterministic the feedback loop is than on the model itself.

tsma -- Regression Defense Line for Legacy Code

tsma -- Regression Defense Line for Legacy Code

A CLI tool that indexes every function, detects test presence, measures coverage, and gives precise feedback to LLM agents. One command builds a regression defense line around legacy code.

filefunc — One File, One Concept

filefunc — One File, One Concept

The navigation unit for an AI code agent is the file. filefunc is a Go code structure convention and CLI tool that enforces one concept per file.