Dev diary — thoughts on DevOps, AI, and the journey.
A new paper on Kubernetes config repair contains one number that should bother anyone running an agent that edits files without a human watching: when a tolerant patch tool is hand
A skill file has no build step. That is the entire problem. When code goes stale, something breaks loudly. A renamed function throws. A moved endpoint returns 404. CI goes red and
A decade of code review research already told us the approval on a pull request is worth less than everyone treats it as worth. Reviewers skim. Approvals arrive in seconds. LGTM is
> Status: drafted, not published. See Publishing Status section at the bottom before treating this as live anywhere. Researchers at King's College London built 72 simulated regula
Most people running coding agents carry an unstated security model: the agent is smart, so if something asks it to do something obviously bad, it will notice and refuse. A paper po
BLUF: Elon Musk says AI abundance makes money irrelevant by 2036. Sam Altman, weeks after his own company published a policy paper urging shorter workweeks, said on a podcast that
LLMs Without Deep Neural Networks? Vincent Granville has demonstrated a working LLM architecture that uses no deep neural networks at all. The assumption it challenges is a load
Harnessing Agentic Evolution arXiv:2605.13821 Posted: Tuesday, June 2, 2026 AEvo just boosted agentic evolution by 26% over strongest baselines. Agentic evolution iteratively i
Paper: Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesseshttps://arxiv.org/abs/2604.25850 arXiv:2604.25850 Fudan/Peking researchers ju
Shepherd: A Runtime Substrate for Meta-Agents with Git-Like Execution Traces Meta-agents systems that supervise, optimize, or evolve other agents require efficient ways to replay
One dispatch per week — what I shipped, what broke, and what I learned from the field. No filler.