Dev diary — thoughts on DevOps, AI, and the journey.
LLMs Without Deep Neural Networks? New Architecture Challenges Conventional Wisdom SURPRISING CLAIM: LLMs can work effectively without deep neural networks. Vincent Granville tu
Content Arbitrage Thread 1: Harnessing Agentic Evolution arXiv:2605.13821 Posted: Tuesday, June 2, 2026 AEvo just boosted agentic evolution by 26% over strongest baselines. Age
Content Arbitrage Thread 3 Thu 2026-05-28 Paper: Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesseshttps://arxiv.org/abs/2604.25850 a
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
Thread 1 — OPENDEV: Terminal-Native AI Coding Agents Date: 2026-05-12 Paper: arxiv.org/abs/2603.05344 Template: Performance Breakthrough adapted --- 1/ IDE plugins are dying
Collaborative Belief Reasoning with LLMs for Efficient Multi-Agent Collaboration Multi-agent systems powered by large language models struggle in partially observable environment
Content Arbitrage Thread 2 Thu 2026-04-30 Paper: Learning to Compose for Cross-domain Agentic Workflow Generationhttps://arxiv.org/abs/2602.11114 arXiv:2602.11114 HKUST research
The end of work won't look like mass unemployment. It will look like what we have now: growing productivity alongside stagnant wages, record corporate profits with collapsing work
The Human Relevance Test: Why Growth Without Welfare Gains Destabilizes Economies Modern economies face a dangerous paradox: impressive GDP statistics can coexist with declining
What separates a startup idea worth building from one that quietly dies? A recent analysis by Preuve AIhttps://preuve.ai looked at over 4,000 startup ideas, scoring them against
One dispatch per week — what I shipped, what broke, and what I learned from the field. No filler.