The new set of problems for engineers to solve
A lot of software engineers are going through what can only be described as an identity crisis. The job has changed a lot. Some are depresse...
Topic
#ai-safety
15 篇笔记
AI Agent 沙箱怎么选？我们把 runc、vArmor 和 Kata 跑了 30 轮
在 104 线程 Linux 物理机上实测 runc、runc + vArmor 与 Kata QEMU：Kata 用近一倍启动时间和数百 MiB 内存换独立内核，vArmor 则以接近 runc 的成本收紧行为边界。
AI agents meant to replace Meta workers made “large-scale, disruptive actions”
Report shows Meta's challenges replacing people with AI agents.
Agent 的 Sandbox 到底是怎么实现的？
从 Codex、Claude Code、Gemini CLI 到 OpenHands很多人讨论 AI Agent 安全时，关注的是：“模型会不会执行危险命令？”但真正重要的问题其实是：即使 Agent 决定执行危险命令，底层系统是否允许它成功？这就是 Sandbox（沙箱）存在的...
Fragments: August 18
fragments 18 Aug 2026
What Is Reasoning
A short summary of how reasoning traces work.
Patterns and problems in multiagent systems
We ran experiments on swarms of Claude agents and found coordination failures, collusion, and sabotage. Here, we share what they mean for AI safety.
The company brain has a permissions problem
Every company is connecting Slack, email, docs and meetings into one brain that gives everyone access to everything the company knows.Nobody...
YC 开源 QM：当每个员工都有 Agent，公司需要怎样的协作系统？
未来一家公司里，可能每个员工都有自己的 Agent。它们能读文件、查数据库、写代码、回复邮件，也能在后台持续运行任务。问题随之而来：这些 Agent 应该看到什么？记住什么？使用谁的账号？哪些能力可以共享？危险动作由谁批准？7 月 31 日，Y Combinator 开源的 QM...
A practical guide to building agents
A comprehensive guide to designing, orchestrating, and deploying AI agents—covering use cases, model selection, tool design, guardrails, and multi-agent patterns.
Towards org-level agent harnesses
Claude Tag has grown rapidly in Anthropic. I want to share some of the reasons for this and the behavioral shifts I’ve seen with this agent ...
30 Core Agentic Engineering Concepts Every Developer Should Know
There are 8 billion people on the planet.Only a fraction of developers understand how AI agents actually work.Not the demos. Not the hype.Th...
AI 101: What is Recursive Self-Improvement?
How AI systems are beginning to automate coding, experiments, evaluation, and research workflows ‒ and why Anthropic, Recursive, and Sakana ...
Loop engineering: the 14-step roadmap from prompter to loop designer.
Most developers still prompt their coding agents by hand. They type, they wait, they read the diff, they type again. 9out of 10 builders hav...
When AI builds itself
Our progress toward recursive self-improvement, and its implications.