Glean 拾遗
中 EN
Submit a link
Daily · timeline

A few picks a day.

Sat, Aug 22, 2026 3picks
← 08-21
Calendar ▾
2026 · 08
MoTuWeThFrSaSu ·····12345678910111213141516171819202122232425262728293031
has picks today
08-23 →
06:00

DeepSeek Harness: A Plugin-Centric Runtime for AI Agents

DeepSeek 开源的 Agent 运行容器：一切皆插件

DeepSeek Harness (dsh) is an open-source agent harness from DeepSeek AI with a plugin-everything architecture powered by Cordis, a framework designed around spatiotemporal composability. It is currently in developer preview, so breaking changes are expected. You can run it from npm or from source, and it launches a local Web UI at 127.0.0.1:3080 by default. The project aims to be a modular runtime for building and operating AI agents, and is suited for engineers who want an extensible, self-hosted agent infrastructure rather than a closed product. Community support is available via GitHub Discussions and Discord, and plugins can use the 'dsh-plugin' topic for discoverability.

github.com · 2 min · Agent Harness · Agent Infrastructure · Agents · Plugin Architecture
06:00

Cordis: A Meta-Framework for Spatiotemporal Composability

基于时空可组合性的插件化元框架

Cordis is a meta-framework introducing spatiotemporal composability, a programming paradigm that enables systems to be composed uniformly across spatial (distributed) and temporal (event/state evolution) dimensions. Built on TypeScript with a plugin architecture, it supports modular expansion. The project is in active development with an unstable API, and the team provides a paper and a primer to clarify the philosophy. Useful for engineers interested in functional programming, modular architecture, and novel programming paradigms.

github.com · 1 min · Effect · Framework · Node.js · Plugin · TypeScript
06:00

Software Engineering Fundamentals Matter More Than Ever

智能体时代，软件工程基本功的价值反而更高

In this reflective essay, a software engineer discusses impostor syndrome and why software engineering fundamentals still matter amid agentic AI hype. Agent harnesses have crossed the "can it be done" threshold, but producing software that is debuggable, maintainable, layered, and composable still requires careful human judgment. LLMs don't truly reason; they predict based on compressed human knowledge, so effective use depends on providing concise data at the right time and deterministic validation tools giving natural-language feedback. The author cites the Illusion of Thinking paper, JEPA/LeCun research, and Simon Willison's "lethal trifecta" about prompt injection and advice filtering. Aimed at engineers who want a grounded perspective on AI-assisted development.

rhonabwy.com · 6 min · Agents · AI Engineering · LLM · Software Engineering