#07
ozanoner/esp-mosaico-microbit
Vibe coding with esp-mosaico targeting a microbit
推荐理由ozanoner/esp-mosaico-microbit：Vibe coding with esp-mosaico targeting a microbit。
周报
2026-W43 周报精选：🤖 AI Agents Weekly: Claude D；Rapidly scaling online stora；Usage metrics API adds usage
Vibe coding with esp-mosaico targeting a microbit
Anti-AI-slop design skill for Claude Code, Cursor, and Codex.
An open-source AI agent that brings the power of Gemini directly into your terminal.
Practical productivity tools for Claude Code, Codex-CLI, and similar CLI coding agents.
Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aw
In today’s issue: Moonshot launches Kimi K3.1 Pro Anthropic previews Claude Duet OpenAI coordinates critical PHP fixes MiniMax opens M3.1 Flash weights Recursive ships local coding model Flint DeepSeek open-sources DeepInfer Ramp details its Laminar harness Inception launches dif
Learn how OpenAI scaled Habitat with reliable multi-tenancy, global caching, and Azure Cosmos DB to deliver 12× faster reads for ChatGPT.
The Copilot usage metrics API now reports model usage from more of the tools your developers use with Copilot, including tools like OpenCode that weren’t previously captured in your reports. A new totals_by_client array is available in the enterprise, organization, enterprise-use
The new GitHub app in Teams brings notifications and Copilot together, helping teams turn issues into fixes and ship code faster without leaving the conversation. Get notified in channels, group chats, or private chats, then @mention GitHub to turn updates into action. Turn an is
2 months ago we covered Z.ai CEO Prof Jie Tang’s prediction that we’d get a Fable-class open weights model by year end . 2 weeks ago Meta achieved a Fable-class model in closed source , but, with 2.5 months left to go, we finally got it - a 2.8T open weights model beating Fable 5
Every Claude Code agent, at a glance, in your Mac's notch Discussion | Link
Teaching a robot to navigate an obstacle course requires more than a walking policy. It must perceive its surroundings, maintain balance, and adjust its actions when obstacles block the path ahead. Developing these capabilities connects several stages: creating assets and an envi
A pet for every Claude Code session Discussion | Link
Fast, focused, low-cost decisions for any application.
Claude Cowork and chat come together for Enterprise
OpenAI 介绍其前沿模型训练与评估环境的安全加固措施，包括训练期间不接入互联网、构建离线缓存网页世界、以纵深防御多层隔离，并用最强模型（含即将推出的 GPT‑6 Astra Cyber）组成智能体团队进行高算力红队测试。
Generative AI
A controlled study shows that switching between coding-agent harnesses like Claude Code, OpenCode, or mini-SWE-agent barely moves pass rates more than rerunning the same setup. Cost per task, however, can triple, driven mainly by the system prompt that gets resent with every step
On Thursday, Pennsylvania Governor Josh Shapiro signed the Artificial Intelligence Deceptive Advertising Act into law, requiring disclosures on AI-generated ads. The law requires any ad - whether it's a still image, video, audio, or text - that "has been significantly modified or
In September, we announced a global default policy for generally available GitHub Copilot features and supported client capabilities on Copilot Business and Copilot Enterprise plans. Starting today, we’re gradually rolling out enforcement of the policy through October 26, so it m
380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketin
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
VCP 部署在 AI 模型 API 与前端应用之间，是面向AGI OS开发和探索的工业级基建示范项目。通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架，将原本“无状态、无记忆、无工具调用能力”的大语言模型，彻底改造成拥有永久自我意识、物理世界操作权及群体协作智能的完整智能体系统。
Fast and Simple Face Swap Extension Node for ComfyUI (SFW)
In order to make it easier to use the ComfyUI, I have made some optimizations and integrations to some commonly used nodes.
Public monitoring now includes alert management capabilities like automatic validity checks to help you triage and remediate leaked secrets at scale. Alert management with dismissals, timelines, and filtering Always-on validity checks for supported secret types REST API and webho
Installing GitHub Apps on your enterprise is now generally available. You can replace classic PATs with GitHub Apps in more of your enterprise and organization automation with the expanded API support detailed below. These new and expanded permissions are focused on governance, s
Anthropic published an 18-minute guide on Oct 22 called "When to fold subagents into your main agent loop." It is aimed at enterprise agent builders, but the lessons apply to anyone who set up a pile of subagents in Claude Code. Main points: - Default to one model, one context wi
We’re adding blob storage endpoints for GitHub Actions on github.com as part of our ongoing work to improve capacity and reliability. The meta API now includes these new endpoints. If your organization uses a network allowlist to access GitHub Actions blob storage, review your ne
Anthropic 发文介绍处于研究预览阶段的 Claude Duet 智能体的安全与隐私设计。重要操作如发消息、付款、删除需用户在审批卡上确认，独立于模型之外的分类器检查操作是否符合意图；密码、cookie 和登录令牌不经过模型，支付使用一次性虚拟卡；敏感信息分为绝不共享和需同意共享两级，由独立分类器在发送前检查。
Tool: Quick Study Prompt to Claude Opus 5.5 High : Build an artifact where you open a photo and it rapidly (in a few seconds) paints a version of that photo using a canvas element and simulated paintbrush See also my previous experiment getting Claude Fable to simulate a watercol
What forward deployed engineering means at OpenAI
Matrix首页推荐Matrix是少数派的写作社区，我们主张分享真实的产品体验，有实用价值的经验与思考。我们会不定期挑选Matrix最优质的文章，展示来自用户的最真实的体验和观点。文章代表作者个人观点 ... 查看全文
Anthropic 发布对 Claude Mythos 5 对齐问题的评估报告。
Learn how Project Chrysalis combines Google Cloud's Gemini Enterprise Agent Platform, Agent Development Kit (ADK), BigQuery, and a four-gate defense-in-depth security stack (Model Armor, Cloud KMS, Binary Authorization, and OPA) to build governed, self-evolving AI agents that rem
Donating Agent Skills to the Agentic AI Foundation News today from Anthropic: We’re committed to keeping Agent Skills open, community-driven, and vendor-neutral. Today, we are donating the standard to the Agentic AI Foundation (AAIF) under the Linux Foundation, which we co-founde
AI developers aren’t just running a single model anymore—they’re orchestrating multiple models in parallel, chaining inference calls, and experimenting with frontier-class architectures that demand hundreds of gigabytes of memory. NVIDIA DGX Spark was built to bring AI developmen
arXiv:2610.01938v2 Announce Type: replace-cross Abstract: Exam-style accuracy does not establish whether large language models (LLMs) reason well over clinical records. We define clinical reasoning as integrating and updating evidence across time and sources to form, revise and j
In May, an internal model at OpenAI found a counterexample to Erdős's unit distance conjecture . Open since 1946. Many experts had tried to prove it. OpenAI found a counterexample instead. A month later, OpenAI published a proof of the Cycle Double Cover (CDC) problem , then solu
arXiv:2610.30014v1 Announce Type: cross Abstract: LLM agents with similar success rates can follow different action sequences. An Agent Behavior Map represents LLM-harness combinations using centered action log-likelihoods on shared reference trajectories, without requiring new e
Anthropic 宣布把 Agent Skills 开放标准捐赠给 Linux Foundation 旗下的 Agentic AI Foundation（AAIF），此前已向其捐赠 MCP。
I have written a lot about reasoning models here over the last two years on Ahead of AI, including a recent article on mechanisms to control reasoning effort levels in contemporary LLMs . Reasoning models are still as relevant as ever. In fact, almost all current-generation LLMs
📌 一句话摘要 本分类包含 70 部美国喜剧科幻电影，涵盖从经典系列如《回到未来》到现代热门如《蜘蛛人：离家日》的广泛作品，展示了该类型在电影史上的丰富多样性。 📝 详细摘要 美国喜剧科幻片是电影中一个独特的子类型，将幽默与未来主义或超自然元素相结合。本分类中的电影包括了各种风格，从家庭友好的动画片（如《小小兵》）到成人向的讽刺作品（如《千万别抬头》）。这些影片不仅提供娱乐，还经常探讨科技、社会和人性的深刻主题，同时保持轻松愉快的基调。 💡 主要观点 类型多样性 分类中的电影涵盖了从家庭动画到成人讽刺的广泛范围，包括超级英雄、外星人、时间旅行和机器人等多
You can now use expiring, automatically refreshing OAuth credentials in GitHub CLI as part of a public preview. When you opt in, gh stores an expiring access token alongside a rotating refresh token and automatically refreshes the token whenever it is needed. You stay authenticat
Warm welcome to Basil Chatha , our newest cohost from the Forward Deployed side of the AI Engineering world! We’ll be ramping up a new show with him and couldn’t pass up an interview with Modal’s CEO Eric on the occasion of their monster Series D! Two years ago, we spoke with Eri
月之暗面发布 Kimi K3.1 系列首个模型 Kimi K3.1 Pro，为 3T 级开放权重模型，上下文窗口 100 万 token，并同步推出速度快 2-3 倍的 Kimi K3.1 Pro Highspeed。
Anthropic Applied AI 团队发布指南，讲解何时把 orchestrator 下的路由器、规划器和领域子智能体合并进单个主 Agent 循环。文中对比显示，带 skills 的单智能体在质量上常优于一提示全包和子智能体设计，且成本和延迟更低，一家客户改用单循环后运行时间约快 2x。
📌 一句话摘要 从 Agent 到多模态 RL Infra 再到具身，王淏楠给出三条技术主线的从业者判断：Agent 智力已够、缺场景与易用性，视频生成仍在半山腰，Astra 让具身第一次看到落地可能。 📝 详细摘要 42 章经曲凯对谈王淏楠——他先后在 MiroMind 做 Agent、在腾讯混元负责多模态 RL Infra 并主导开源框架 UniRL，现于一家具身智能公司负责基模预训练。节目沿他的三次转向展开：先谈 Agent 与多模态的取舍，认为 Agent 已是交互主线，智力足够，短板在场景覆盖与易用性，个人 AI 是长期终点；国内 RL 与海外
The Great Day of His Wrath, by John Martin, via WikiArt . Welcome to the reading list, a weekly roundup of news and links related to buildings, infrastructure and industrial technology. This week we look at minimum lot sizes, Boeing’s next 737 MAX, Fervo short sellers, Figure AI’
Mistral is collaborating with NVIDIA to develop a new generation of AI-native engineering workflows powered by NVIDIA accelerated computing.
OpenAI 接近完成至多 300 亿美元的新一轮融资，但将估值目标从最初的 1.4 万亿美元下调至 1.25 万亿美元。
An AI agent can complete its assignment and still cross a security boundary. Recent incidents show that agents can circumvent security controls while using tools, credentials, and services to pursue their assigned goals. Monitoring and enforcement need to operate outside the agen
Autonomous agents can work for hours on complex tasks, accessing files, tools, the internet, and spawning other agents to collaborate with. Executing complex tasks over long time horizons leads to compounding risk: the agents may download code, build new tools, request additional
国务院办公厅 10 月 23 日印发《关于适应人工智能技术发展助力构建就业友好型发展方式的意见》，提出增强 AI 创造就业机会、赋能传统岗位的正面效应，有效减缓 AI 应用的就业替代影响。
AT&T is working with OpenAI to make legal knowledge easier to access. Learn how its LegalEdge team is rethinking intake and scaling legal judgment.
Claude Security now keeps up with your repositories as code changes, tracks findings until they’re fixed, learns from the context your team adds, and connects to your tools through an API and MCP. Available in public beta for Claude Enterprise customers.
arXiv:2610.28259v1 Announce Type: new Abstract: Recent advances in visuospatial understanding and agentic reasoning enable direct robotic manipulation with general-purpose multimodal models, but their embodied capabilities remain poorly understood. This paper systematically evalu
arXiv:2610.27350v1 Announce Type: cross Abstract: Frontier models can control robots through agent harnesses that loop on one question: what motion comes next toward the user's goal? We show that this default loop carries out harmful instructions. With GPT-6 Astra controlling a l
Tags: Customers Health The post Before the ambulance arrives: How AI is helping the NHS rethink patient care appeared first on Source .