administration of a Linux system is done by editing text files, since pretty much all settings of the system are a defined in some text file. this quirk has, by accident, turned into a UX superpower in the age of text-based AIs, which will fix your problem... by asking it to do so.
Jan 14, 2026 at 5:48 AM
Joshua Gu on Twitter / X
Recent agentic systems (Claude Code, Codex, RLM, etc.) push context out of the prompt and into the environment (e.g., as files). This helps them maintain long-term knowledge about their goals and functionality.🚨 While this is a good idea, we show a surprising result: systems… pic.twitter.com/XHFVaDcr4l— Joshua Gu (@astrogu_) May 20, 2026
AI agent runs amok in Fedora and elsewhere
Agentic AI systems can be used to do a variety of things autonomously on behalf of a human user [...]
From chatbots to assistants: governance is key for AI agents
AI's shift into agentic technology ushers in a new set of governance and security challenges that will mean defining to what extent they should be autonomous
Nothing new under the sun: everything is a file
The Unix revolution was built on a key principle: everything is a file. Now, with the rise of AI Agents, LLMs have access to half a century of file-based arcana. The result? Everything is becoming a file again.
Agentic AI Governance: Securing Autonomous AI Agents in Enterprise
When AI agents start making decisions, calling tools, and coordinating with other agents without waiting for human approval, the governance playbook most...
Stop Begging Billionaires To Fix Software — Build Your Own
This is part one of a two-part series on using AI tools as one piece to fight back against tech company control of our lives. Part two shares the details of how I built my own task management tool …
The Postman Drop: Introducing the AI Agent Builder
The AI world moves fast, and we’re now entering the era of AI agents. These sophisticated AI systems integrate reasoning and memory, enabling them to autonomously interact with tools, make decisions, execute tasks, and deliver real-time results. AI agents will play an increasingly central role in how organizations operate, which Abhinav Asthana, our co-founder and CEO, discussed in a recent blog post. But systems this powerful are extremely challenging to build—especially without a unified solut...
Artificial intelligence in government: why people feel they lose control
The use of Artificial Intelligence (AI) in public administration is expanding rapidly. While AI promises greater efficiency and responsiveness, its integration into government and administration ra...
MI9: An Integrated Runtime Governance Framework for Agentic AI
Agentic AI systems capable of reasoning, planning, and executing actions present fundamentally distinct governance challenges compared to traditional AI models. Unlike conventional AI, these systems exhibit emergent and unexpected behaviors during runtime, introducing novel agent-related risks that cannot be fully anticipated through pre-deployment governance alone. To address this critical gap, we introduce MI9, the first fully integrated runtime governance framework designed specifically for safety and alignment of agentic AI systems. MI9 introduces real-time controls through six integrated components: agency-risk index, agent-semantic telemetry capture, continuous authorization monitoring, Finite-State-Machine (FSM)-based conformance engines, goal-conditioned drift detection, and graduated containment strategies. Operating transparently across heterogeneous agent architectures, MI9 enables the systematic, safe, and responsible deployment of agentic systems in production environments where conventional governance approaches fall short, providing the foundational infrastructure for safe agentic AI deployment at scale. Detailed analysis through a diverse set of scenarios demonstrates MI9's systematic coverage of governance challenges that existing approaches fail to address, establishing the technical foundation for comprehensive agentic AI oversight.
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user. This study describes its comprehensive architecture by analyzing the publicly available TypeScript source code and further comparing it with OpenClaw, an independent open-source AI agent system that answers many of the same design questions from a different deployment context. Our analysis identifies five human values, philosophies, and needs that motivate the architecture (human decision authority, safety and security, reliable execution, capability amplification, and contextual adaptability) and traces them through thirteen design principles to specific implementation choices. The core of the system is a simple while-loop that calls the model, runs tools, and repeats. Most of the code, however, lives in the systems around this loop: a permission system with seven modes and an ML-based classifier, a five-layer compaction pipeline for context management, four extensibility mechanisms (MCP, plugins, skills, and hooks), a subagent delegation mechanism with worktree isolation, and append-oriented session storage. A comparison with OpenClaw, a multi-channel personal assistant gateway, shows that the same recurring design questions produce different architectural answers when the deployment context changes: from per-action safety classification to perimeter-level access control, from a single CLI loop to an embedded runtime within a gateway control plane, and from context-window extensions to gateway-wide capability registration. We finally identify six open design directions for future agent systems, grounded in recent empirical, architectural, and policy literature.
Hermes Workspace · Your AI agent’s command center
Chat, memory, skills, terminal, and files — one interface for everything your agent does.
cmux - The terminal built for multitasking
Free and open source macOS terminal for AI coding agents. Works with Claude Code, Codex, OpenCode, Gemini CLI, Kiro, Aider, and any CLI tool.
Can AI Be Governed? Only If We Build Normatively Competent AI
Hadfield's discussion brings the idea of AI governance back to the core idea of steering the behavior of an AI system. As she notes, this not only involves technical questions about how AI systems ar...
Agentic AI Governance: A Strategic Framework for Autonomous Systems
Agentic AI is moving from chat to action. Learn how to govern autonomous systems using the "Digital Contractor" framework and the 3-Tiered Guardrail system.
