与「running」相关的搜索结果

Meet the Gemma Translator! A fully offline device powered by Gemma 4 E2B built with @Antigravity. Running entirely on a Raspberry Pi 5 with a connected microphone and speaker, this highly portable prototype is housed inside a custom, 3D-printed case.

Ladies and gentlemen, it's time to pass the torch and demote myself to my natural state: a poster. I'll be stepping back from leading product for 𝕏 and will continue on as an advisor. Serving the X community has been the privilege of a lifetime. X is, and will remain, the most important communication technology in history. But running this app is a 24/7 job and it's now time for me to take a breather. The app is seeing unprecedented growth in new users & engagement. We continue to break records every month. We've climbed 70 spots in the App Store since this time last year. And in the last 400 days, we rebuilt almost every aspect of X: the Timeline, the Android app, onboarding, notifications, chat and more. We also launched nearly 30 new products while protecting the integrity of the town square: becoming the first app to show Country-of-Origin on profiles and mounting defenses against AI bots. There's certainly much more work to be done, but our foundation is stronger than ever. None of this would have been possible without the incredible team here. The next leaders will take X to even greater heights with @benjitaylor on design, @singhai on core product engineering and @dinkin_flickaa on mobile engineering -- among many other great people. Thank you to Elon and the X team for welcoming me into the company. See you on the Timeline.

Introducing Prime Agent: A self-improving RLM harness for coding and long-running autonomous tasks. Designed to be both token-efficient and expressive through programmatic tool calling, context as a variable, multi-agent messaging, and a self-modifiable harness state.

开发系统最极致高效的Agents.md，没有之一： # AGENTS.md ## Core Principles - Choose the simplest implementation that fully satisfies the current requirements. Avoid unnecessary abstraction, configuration, indirection, or speculative extensibility. - Make the smallest necessary change that fixes the root cause. Do not refactor unrelated modules or change strategy semantics unless explicitly requested. - Grow the system in layers. Start from the smallest working end-to-end version and add new capabilities incrementally. Never replace a working system with unfinished complexity. - Reuse existing project components before creating new ones. Prefer extending proven modules over introducing parallel implementations. - Prefer well-maintained libraries when they reduce overall complexity or improve reliability. Do not reimplement common functionality without a clear benefit. - Keep components modular with clearly defined responsibilities. Avoid unnecessary coupling between strategy logic, execution, accounting, replay, and infrastructure. - Design for long-term maintainability once a feature or strategy has been validated. Do not over-engineer speculative ideas before evidence exists. --- ## Strategy Development - Validate hypotheses with historical replay before introducing forward-only logic whenever historical validation is possible. - Every trading strategy must progress through Replay → Shadow → Canary → Live. Do not skip validation stages. - Base design decisions on measurable evidence rather than intuition. Optimize only after demonstrating that an edge exists. - Treat every strategy as an independent contract. Do not silently alter frozen behavior without explicit authorization. --- ## Existing Systems - Do not break running Shadow or Live systems for unrelated work. - Preserve compatibility only when required by active production or validation workflows. Otherwise, remove obsolete code instead of accumulating compatibility layers. - Reuse existing infrastructure whenever possible, including replay engines, accounting, execution, wallet management, order book handling, logging, monitoring, and daemon frameworks. --- ## Engineering Standards - Prefer deterministic behavior over hidden automation. - Fail loudly when assumptions are violated. Do not silently ignore errors or fall back to unexpected behavior. - Keep configuration minimal. Introduce new configuration only when behavior genuinely needs to vary. - Remove dead code instead of leaving unused paths behind. - Write code that is easy to inspect, replay, test, and reason about. - Keep implementation consistent with existing project architecture unless an architectural change is explicitly requested. --- ## Scope Discipline - Implement only the requested scope. - Do not introduce unrelated optimizations, redesigns, migrations, or feature expansions. - Non-blocking findings outside the requested scope may be noted separately but must not be merged into the current task. - Consider a task complete once its agreed acceptance criteria are satisfied. Treat subsequent improvements as separate work items.

Imagine driving a single route that takes you along China's entire land border and coastline. That is exactly what a massive new 27,000-kilometer loop will make possible. According to the Ministry of Transport, China plans to build this super-highway during the 15th Five-Year Plan period (2026–2030) by linking three major routes—the G219, G331, and G228—end to end. Tracing the country's borders and coastline, the journey will stretch more than half the length of the Earth's equator. Far more than a transportation corridor, the route weaves together hundreds of scenic areas and historic cities, offering a journey across some of China's most diverse landscapes. G219 runs about 10,000 km from the Kanas Scenic Area in northwest China’s Xinjiang to Dongxing in south China's Guangxi, crossing deserts, the Qinghai-Xizang Plateau, the Himalayas, and other spectacular terrain. G331 stretches about 9,200 km along China's northern border, taking travelers through the vast grasslands of Inner Mongolia, the fertile plains of northeast China, and iconic destinations including Fuyuan, Mohe, Changbai Mountain, and the Greater and Lesser Khingan Mountains. G228 extends about 7,400 km from Dongxing in Guangxi to Dandong in Liaoning Province, linking China's coastal provinces and dozens of seaside cities. Running across major rivers including the Pearl, Yangtze, Yellow, and Yalu, it offers sweeping views of the country's coastline. If you could explore one part of this epic loop, where would you start?

Someone 'accused' me of vibe coding the LFRR simulator. I've been coding since 1982, I've hand assembled machine code, injected fixes into running processes, worked on software that's made it to Mars and worked as a software developer for decades. OF COURSE I USED AI CODE TOOLS

Grok Build just got another meaningful upgrade, bringing permanent session deletion, smarter diagnostics, better keyboard guidance, and stronger reliability across session management, background tasks, and compaction Release Notes: v0.2.118 Features: • Sessions can now be permanently deleted from the dashboard by pressing Ctrl+X twice on an idle row, or from the welcome list with d then y. • Keyboard shortcuts help (Ctrl+.) now shows how to browse prompt history and search the conversation. • grok doctor now warns when tmux is reducing colors and can fix the config. Bug Fixes: • /btw now retries on temporary model overload instead of failing immediately. • Session sharing is temporarily disabled. • [stop] / Ctrl+C during /compact now cancels instead of no-opping. • Automatic recaps no longer appear twice after the same turn. • Background task wait timeout descriptions and limits now match the client's actual configured ceiling. • Background tasks no longer stay stuck as 'Running' in the tasks pane when they finish quickly. • Plan mode indicator now disappears right after approving a plan instead of lingering. • Dragging the scrollbar in the plan preview now works as expected. • Compaction now correctly handles certain context-length errors from the inference API.

给关注了半年的agent team 交份作业。 这是一篇2w字长文，也是一份 Agent Team 的最佳实践。 01 一个 Agent，是怎么变成多个 Agent 的为什么真实工作会把 Task Agent 推向 Long-running Agent；为什么一个越来越好用的 Agent 最后又必须分化；多个 Agent 出现以后，瓶颈为什么会转移到 Human。 02 先让“谁负责什么”离开 Human 的脑子Agent 怎样获得稳定身份、Domain 和 Scope；Human 与 Agent 怎样查询当前 Team 的责任结构；真实协作又怎样逐渐沉淀为 Organization 与 Collaboration。 03 让 Agent 自己开始协作Agent Message 带来了什么变化；一个 Agent 怎样把工作直接交给另一个 Agent；为什么 Agent 沟通不是一次把一切说完。 04 Message 负责沟通，Topic 负责收口当工作跨越多个 Agent、多个 Turn 和多天以后，怎样保留唯一的当前版本；Responsible、Participant、Artifact 和 Needs You 分别解决什么问题。 05 Overview：让一支持续变化的 Agent Team 变得可治理当 Human 不再阅读每个 Agent 的全部过程，怎样从更高层观察 Team；怎样发现等待、积压和瓶颈候选；为什么治理关注的是工作流动，而不是让每个 Agent 看起来都很忙。 06 Agent Team 怎样进入真实的外部关系为什么把 Agent 接入 Slack、飞书还远远不够；Agent 对外以后，身份、角色、信任、权限和现实后果为什么必须被分别治理。 07 CodexLoom 在织什么Multiple Agents 与 Agent Team 的真正分水岭是什么；Human 在 Team 中的新位置是什么；为什么需要稳定的 Agent 和动态的 Team。