与「issue」相关的搜索结果

Codex 5.6 真的绝了 用了这么久，最值得装的插件就这几个 👇 ① Browser AI 自动操作浏览器，点击、输入、端到端测试全能干，再也不用手动验证了 ② GitHub 和 Issue、PR 打通，丢个任务给它，从编码到审核全搞定，开发流程快到飞起 ③ Codex Security 自动扫代码漏洞和密钥泄露，还能给出修复方案，省了一堆安全问题 ④ Build Web Apps 描述想法就行，设计、开发、测试一条龙，全栈项目的时间能省一半 ⑤ Figma Figma 设计直接转代码，响应式自动搞定，设计稿和代码终于能对上了 ⑥ Sentry 线上报错自动分析，帮你定位问题还给出修复代码，线上问题不再头大 但最绝的其实是「Sites」功能 开发完直接在里面预览，一键公开分享 还能用自定义域名 这意味着什么？原型秒送客户看 把这些组合起来用 Codex 就从单纯的「写代码 AI」变成了真的开发团队——设计、编码、测试、调试、上线全包

太它妈方便了，多年的程序员都不想写自动化了 微软开源了个有意思的东西，叫 Skill Recorder。 你只要录一遍自己怎么完成一个任务——它会会采集鼠标操作、窗口切换、网页、剪贴板、终端命令和语音讲解——录完之后通过 GitHub Copilot CLI 直接把这套流程重建成一个 SKILL.md，定好自动化。 任务意图 → 通用步骤 → SKILL.md → 定时自动化 说白了它不是传统 RPA 那套靠录屏重放像素坐标，而是把你的网页点击转成更稳定的 API、CLI 或 Agent 原生工具。 举个例子，你演示一次处理 GitHub Issue，它可以基于这条录制生成一个能够批量处理同类 Issue 的 Agent Skill。 目前原生支持 Microsoft Scout 和 Microsoft 365 Copilot Cowork，暂时还不直接支持 Claude Code、Codex 和 OpenCode，但生成的 SKILL.md 可以手动适配。 它代表的是 Agent 工作流的一个方向：不是教 AI 怎么做，而是直接做给 AI 看。 想试的自己扒下来跑一遍，GitHub 872 星还很新，项目还在快速迭代。

有幸收到飞书团队的邀请，分享了我们团队近期在做的 Vibe Coding 项目——dashi-taskboard 🚀 这是一套重塑现有 Codex 工作流的项目管理工具，通过任务看板的方式，把你从海量的 Codex 对话中拯救出来。 项目现已在 GitHub 完全开源，欢迎大家安装体验、提 Issue 和反馈建议！

Mole CLI just passed 60K stars. It started as a few hundred lines of code I wrote by a pool in Sanya last October. Now: 55 releases, 112 contributors, 812 issues resolved. It also grew into Mole Mac, the pro version with a native GUI and much more. 4 aha moments from using it myself: 1. Got a notification that my AirPods were low on battery. AI suggested it while I was building battery health, and I shipped it. Works for any Bluetooth accessory. Helpful, never noisy. 2. I use Mole daily and it still found 1 TB to clean. Rust target folders add up fast. One scan, gone. 3. Keep Screen On now has 3 modes. Head out on a weekend, your AI coding agent keeps working, you steer it from your phone. 4. Your iPhone battery now shows next to your Mac. All your devices in one quiet dashboard. None of these were my idea. All came from early users, and now they help me every day.

开源项目 LoopX：超长程 Agent 自主运行 200+ hours，状态不漂移。 我的技术主张是：LLM 上下文有限，长程 Agent 需要外置状态，通过完备的状态管理、监督和规划，让 Agent 无人干预时跑得稳、持续有产出；有人干预时跑得更好，能吸收反馈继续演进。 两条真实 trajectory 分别跨越 220.7 / 272.9 小时，跨多轮执行、等待、人工决策、writeback 与 resume 后，整个 loop 仍能找回目标、证据和下一步。 目前 LoopX 已有 3 个 showcase：auto PR issue fix、AutoML experiment 和 auto coredump fix。 以 OpenViking 开源仓库的 PR issue fix 为例，Agent 不只是循环写代码。它需要持续理解 issue 的不同状态，判断何时开发、何时等待、何时请求 review，处理 CI、冲突和上游变化，并连续交付多个 PR。 这对应 LoopX 的 domain state 管理：领域系统决定真实状态，LoopX 负责把状态投影成下一步可执行的工作。 与此同时，Agent 还可以在干活过程中实现能力自进化。当它发现现有系统缺少某项能力时，可以提出 feature、完成开发与验证、发布新的离线或在线版本，再使用新能力继续原来的任务。 长程 Agent 天然适合自进化，“完成工作”和“升级完成工作的系统”可以在同一条长程轨迹中发生。 LoopX 把这些信息外置成结构化控制面： • Goal / Vision：目标是什么，什么不能被局部优化牺牲 • Todo / Gate：当前执行的 frontier，以及必须留给人的关键判断 • Identity / Authority：谁能 claim、writeback、approve • Evidence / Receipt：每次推进留下什么可回读证据 • Quota / Scheduler：何时继续执行，何时安静等待 • Handoff / Recovery：换模型、换会话、换 host 后如何恢复 你也可以把它理解为一块专门给 Agent 设计的可执行 Kanban。 普通看板只展示“谁在做什么”；LoopX 的状态会直接约束和驱动下一次 bounded turn，让看板本身成为执行系统的一部分。 这套系统最强的地方是通用性。它不只可以修 PR，还可以做 auto research、长期实验、自媒体运营、复杂 feature 开发和办公任务。 Agent 不再只是一次性的回答机器，而可以围绕一个人的 vision，长期工作、等待、吸收反馈、积累证据并持续演进。 LoopX 从一开始 build in public：状态协议、CLI、控制面实现和真实运行轨迹都进入了开源仓库；它也已经和 OpenViking、NoKV 等 agent infra 项目形成了开源合作伙伴关系。 我希望 LoopX 最终能放大每个人的 vision 和想象力。只要你有自己的目标、想法或技术主张，就能拥有一个全天候继续工作和探索的 Agent 系统，帮助你把愿景一点点变成现实。 欢迎试用、提 issue、贡献代码，或者用一个真实的 multi-day task 跑 LoopX。

Here is my AI investing guide. Sitting here August 2026, my current best thoughts are as follows: 1. LPS (Land Power Shell) is still the most obvious and fastest path to cash on cash returns. Lots of value can be assembled and traded quickly at this layer. And as data centers get more pushback, energized land can explode in value. Very bullish here. I’ve stepped into this layer very aggressively. My partner @anitavlallian and I have acquired almost 6GW coming online in a ramp from today thru 2029 of grid power and behind the meter. 2. Silicon - I helped get @GroqInc off the ground in 2015 and we licensed it to @nvidia for $20B Dec2025. I won’t invest or incubate anything in this layer now. The perf demands of the chips are too high, manufacturing precision is too complex and supply chain influence to get adjacent components like memory isn’t possible for a startup anymore. Lots of capital will be wasted here chasing Groq and Cerebras’ success. Note that both startups made sense a decade ago when these constraints were much more modest. 3. Clouds - Clouds are very very lucrative but very hard to build and very expensive and technically complicated to maintain. And as alignment becomes a more important issue, I expect the clouds will be asked to build robust KYC and attest to it. This makes the risk:reward ratio skewed. I don’t want to be responsible when the USG says a cloud allowed a bad actor to do something bad because of poor KYC. 4. Models are complicated. The big open question is how much of the revenue being generated by them today is because of tokenmaxxing and poor model behavior. If it’s a lot, then the annualized revenues will diminish meaningfully even as token consumption inflects upwards. This is the big economic question at this layer. 5. Harnesses are where the action is and why I started @8090solutions two years ago. In a nutshell, the harness helps enterprises owns their proprietary context (what Alex Karp calls their ‘alpha’). This is an enterprise’s data, workflows, evals, and business rules. A harness that gives this to an enterprise is what creates very low model-agnostic switching costs, which further reinforces my views of #4# above. 6. Applications will be another long term winner along with harnesses. This is where the differentiation between “off the shelf” and “custom time and materials” melts away. Every company, with the right harness, can now imbue their alpha into the software that runs their company. I expect this to mean that “off the shelf” is largely replaced with custom software creating a huge opportunity to write these solutions for companies. Build once and sell repeatedly is a laggard GTM motion for a SaaS world that isn’t needed here. Think custom by design, alpha embedded, proprietary by nature. Fin. Good luck to all the players!

Watch the full recording of our Q2 2026 earnings call. Prepared Remarks 00:00:00 - Welcome 00:01:20 - 843,775 BTC, 203,683 sats per share, $17B raised year to date, and Strategy’s position as the largest institutional holder of Bitcoin 00:03:27 - Q2 balance sheet: $49.7B of digital assets, $3.75B current USD reserve, lower debt, higher preferred equity, and strong stress-case coverage 00:08:57 - Bitcoin KPIs: 4.5% BTC Yield, 29,997 BTC Gain, and ~3.6x growth in Bitcoin per share since 2020 00:12:47 - Q2 execution: higher Bitcoin holdings, lower debt, larger USD reserves, stronger Bitcoin per share, and active capital management 00:15:03 - Strategy as a net buyer of Bitcoin and net issuer of Digital Credit: 48x more BTC bought than sold and 300x more Digital Credit issued than repurchased 00:18:47 - Returning $STRC to $99–$100 through USD reserves, Bitcoin monetization, repurchases, dividend management, and disciplined issuance 00:24:50 - Bitcoin liquidity: why Strategy’s bitcoin purchases and sales are not material to overall Bitcoin trading volume 00:33:03 - Bitcoin as Digital Capital: website metrics, the 200-week moving average, current headwinds, Bitcoin Dominance, banking adoption, and security coordination 00:44:08 - $STRC as flagship Digital Credit: liquidity, lower volatility, market depth, yield, investor base, path to par, and updated credit metrics 01:05:04 - Equity framework: hurdle rate, breakeven rate, floor rate, market skepticism, $MSTR outperformance, franchise advantages, and Strategy’s long-term ambition Q&A 01:19:31 - Why Bitcoin-backed borrowing is not currently the preferred path to build USD reserves 01:23:11 - Why Strategy is consolidating around $STRC instead of creating more instruments or selling volatility 01:40:37 - Equitizing, repaying, or refinancing convertible debt 01:43:18 - Covered calls, cash-secured puts, Digital Credit, Bitcoin as money, and marketing products to the 99% outside Bitcoin 01:59:22 - USD reserve minimums and the path to $STRC trading at par 02:00:55 - Amplification, USD/BTC reserve mix, and countercyclical capital management 02:12:04 - Why Strategy does not intend to issue $STRC below par 02:20:34 - Lessons from 2022 and 2026, tokenized securities, Digital Money, and the June 26 dislocation 02:34:54 - Closing remarks