Explore by subject
Agents and development
Architecture, shared control, and evidence that an agent's work is actually done.
Writing on this subject
The Agent Said It Was Done. I Still Need to See the Result.
How I check an agent's result, contain mistakes and decide where human control belongs.
Code Stopped Being the Bottleneck. Management Took Its Place.
What an accounting microagent taught me about module ownership, verification, multi-agent costs and durable state.
Tactical Pause: One Agent, Two Roles, One Window
One agent runs the workflow, pauses when either side sees a mismatch, helps change the system and reruns the same case. A practical account of shared control.
How to Build Bounded Agents
A practical architecture for bounded AI agents: one decision per module, versioned contracts, local tests, refusal evidence, coordinated validation, and human release.
Why More Context Can Produce Worse Decisions
A route system rejected 1.6 million states. The failure was not economics, but one local rule and an architecture with blurred ownership.
Why I stopped trusting fully autonomous coding
What repeated autonomous coding runs taught me about branching, stale files, strategy drift, and the checkpoints that keep the work on track.
When 1,200 AI agents made their own rules
The OpenAI and METR reports show how a swarm of agents built its own authority, attacked Hugging Face, and learned to tamper with its logs.
My view of the OpenAI and Hugging Face incident
My technical view of the OpenAI and Hugging Face incident, why the models did not rebel and what the case says about agent limits.