写作
项目与实践
筛选文章 项目与实践
项目与实践
第 2 页 · 12 / 53-
Jev-Code-Reviewer:大 PR 先分 P0/P1/P2 Jev-Code-Reviewer 给 PR 改动做注意力排序,默认展开 P0,同时保留原始 diff 和失败回退路径,帮助人先看关键改动。
-
GitHub Security Lab makes fuzzing an agent feedback loop GitHub Security Lab Fuzzing Taskflow uses coverage gaps to guide model decisions while deterministic tools execute, measure, and persist results.
-
GitHub Security Lab 把 Fuzzing 做成 Agent 反馈环 拆解 GitHub Security Lab 的 Fuzzing Taskflow,模型根据 coverage 缺口决定下一轮,确定性工具继续负责执行、测量与持久化。
-
Link CLI lets agents pay without real card numbers Stripe Link CLI separates purchase intent from payment permission. Agents request a purchase and receive one-time credentials only after user approval.
-
Link CLI 让 Agent 付款,但不拿真实卡号 Stripe Link CLI 让 Agent 先提交购买请求,用户确认后再获得本次支付需要的一次性凭证,把购买意图和支付权限分开。
-
LobsterAI: send tasks by phone, run them on your desktop LobsterAI connects phone messages to a local desktop agent. The phone handles tasks and approvals while the computer works with files, terminals, and browsers.
-
LobsterAI:手机发任务,本机 Agent 继续干活 LobsterAI 把手机消息接到本机桌面 Agent。手机负责下任务和确认,本机继续处理文件、终端、浏览器和项目。
-
json-render constrains UI with a component catalog Vercel Labs json-render defines components, actions, and data bindings before generating schema-constrained JSON that can be checked and replayed.
-
json-render:先锁组件目录,再让 AI 生成界面 Vercel Labs 的 json-render 先定义组件、动作和数据绑定目录,再让模型生成符合 schema 的 JSON。生成式 UI 的边界因此可以验证、记录和回放。
-
A Minecraft agent separates planning from fast decisions This Minecraft agent uses Astra for slow planning, JEV for frequent action selection, and Mineflayer for execution, with logs and scripts to verify runs.
-
Minecraft Agent 把规划和即时决策拆成两层 这个 Minecraft Agent 让 Astra 负责慢规划、JEV 负责高频动作选择、Mineflayer 负责确定性执行,并用日志和验证脚本保留运行证据。
-
OpenCloak: replace personal data before sending it to AI OpenCloak replaces names, emails, and other personal data with stable stand-ins locally, then restores them when the model responds.