Tag / The engineering notebook
AI Agents
13 articles and notes on this topic.
Version One Is Cheap Now. What ArtCraft's AI-Built Clones Teach Software Engineers
In two weeks, one small team used coding agents to publish open-source reimplementations of Photoshop, Premiere, Acrobat, Word and Excel. I read the repositories to see how they were built, how far along they really are, and what commercial users still depend on. My conclusion: version one of software is becoming cheap, and the valuable work moves to fit, verification, support and risk.
AI Can Write the Code. But Code Was Writing Us.
Writing software helped shape how we think as engineers. As AI takes over more implementation, I worry about discovery debt: the questions and insights we miss when we skip the work that might have revealed them. Here is how I want to preserve understanding, curiosity, and judgment while working with coding agents.
AI có thể viết code. Nhưng chính code từng tạo nên chúng ta.
Lập trình từng đồng thời tạo ra phần mềm và người kỹ sư. Khi AI tách hai quá trình ấy, chúng ta có thể tích lũy một loại nợ khó nhìn thấy: những hiểu biết không bao giờ xuất hiện vì không còn phải vật lộn với việc triển khai. Làm thế nào để giữ lại những va vấp tạo nên khả năng phán đoán?
Ask, or It Will Guess: Question-Asking Is the Core Skill of Agentic Work
Models almost never ask you what you meant: across ambiguous questions, answer rates run above 95% and clarification barely registers. Repairing that in conversation makes it worse: underspecified multi-turn runs measure a 39% average performance drop, driven by a 112% jump in unreliability, and the effect shows up from two turns onward. The leverage is no longer in writing better prompts. It is in forcing the questions out before the first answer attempt, and in asking the questions afterward that prove you understood what you shipped.
The Bottleneck Moved to Review: My SDLC After AI Writes Most of the Code
When a machine writes most of your diff, the constraint stops being how fast you type and becomes how well you review. Here is the SDLC I actually run (the provenance audit, the sandbox, the CI backstops, and the three questions I ask every AI-authored change) plus the parts of review that don't compress and never will.
Plan Once, Then Act: When the ReAct Loop Is the Wrong Harness for Small Local Models
On small local models, the standard ReAct loop has a failure mode nobody warns you about: the model calls one tool, declares victory, and stops. What we measured across 12 GGUF models in EdgeVox, why we added a plan-once dispatcher, and how to decide which loop your task actually needs.
NVIDIA OpenShell: Policy-Enforced Sandboxes for Autonomous Coding Agents
NVIDIA just open-sourced OpenShell, a policy-enforced sandbox for autonomous AI agents. Four security layers, a privacy router that decides which LLM sees which data, and hot-reloadable YAML policies. How it works and what it solves that nothing else does.
Bảo mật ứng dụng viết bằng vibe coding: hướng dẫn thực tế để tránh bị tấn công
Vibe coding giúp đưa ứng dụng ra thị trường nhanh hơn, nhưng cũng làm tăng nguy cơ phát hành lỗ hổng bảo mật. Bài viết phân tích các sự cố thực tế, quy trình phòng thủ nhiều lớp và những phương pháp rà soát bảo mật mới với AI.
Securing Vibe-Coded Apps: A Practical Guide to Not Getting Hacked
Vibe coding is shipping apps faster than ever, but also shipping vulnerabilities at alarming rates. This guide covers real disasters, practical security measures from secret scanning to endpoint hardening, and SOTA AI-powered review methods to keep your vibe-coded apps from becoming the next breach headline.
Coding is not fun anymore?
Coding isn't what it used to be. AI implements faster than we can type, and agents are automating our tasks. But there's a bright side: we're evolving from implementors into architects and reviewers. Here's how to survive the shift.
Lập trình không còn vui nữa?
AI có thể viết mã nhanh hơn tốc độ chúng ta gõ và đang tự động hoá ngày càng nhiều công việc thường ngày. Vai trò của kỹ sư vì thế chuyển dần từ người trực tiếp triển khai sang người thiết kế, đánh giá và chịu trách nhiệm cho toàn hệ thống.
Agent Sandboxes: A Practical Guide to Running AI-Generated Code Safely
AI agents don't just talk. They execute code, which makes isolation the whole problem. The sandbox technologies that matter (microVMs, gVisor, WebAssembly) and the platforms built on them (E2B, Modal, Northflank).
Sandbox cho AI agent: chạy code do AI sinh ra sao cho an toàn
AI agent không chỉ sinh văn bản mà còn trực tiếp thực thi mã. Bài viết phân tích các công nghệ sandbox như microVM, gVisor và WebAssembly, cùng những nền tảng phổ biến được xây dựng trên chúng.