AI Coding Live News

On November 10, Cursor rebuilt Projects for multiplayer. You can invite teammates into a Project, and everyone plans, builds, and ships in one workspace alongside their coordinator and worker agents. A new shared context layer holds requirements docs, diagrams, tech specs, and mockups, so a decision made in one chat is visible to every agent in the Project. A shared task board shows who is doing what, what each agent is working on, and the PR behind each task. Agents belonging to different teammates can also talk to each other: they share plans before starting, flag conflicts while working, and unblock each other. The beta is rolling out to all Cursor users starting today.

Zoom

At KubeCon North America on November 10, NVIDIA contributed OpenShell, its open-source security runtime for AI agents, to CNCF as a Sandbox project. OpenShell enforces access to files, networks, credentials, and model endpoints in the infrastructure outside the agent. The project is moving from NVIDIA's GitHub to the neutral ai-openshell organization and is adopting Cedar, another CNCF project, as its policy language. NVIDIA is also contributing to Google-led Agent Substrate and released three open-source Kubernetes components: NVKE, NVKR, and Snapshot. Teams running agents on Kubernetes now get a vendor-neutral permission and isolation layer.

Zoom

On November 10, Meta FAIR researcher Swann Bessa announced e-means on X, a clustering algorithm that replaces classic Lloyd k-means and is open-sourced in FAISS 1.16.0. It swaps full-batch iterations for mini-batch updates with exponential moving averages, and fitted scaling laws set the batch size and step size automatically, so k is the only setting. The paper says that on a range of embedding datasets e-means beats the loss Lloyd reaches after 25 epochs in 1.4 to 2.6 epochs, running 10-45x faster than Flash-KMeans on GPU and 8-15x faster than FAISS k-means on CPU (authors' figures). Teams building vector indexes, RAG pipelines, or dedup jobs can speed up this step directly.

Zoom

On November 10, Anthropic added two new artifact types to Claude: Claude Whiteboards, a board teams can edit together, and Claude Sheets, a shared spreadsheet with tabs, formulas, and drop-downs, both in beta on all paid plans. Claude Dashboards, which entered beta in October, is renamed Claude Data and is now generally available, adding data stories, certified queries, and live sharing. Interactive connectors can now open full apps such as Adobe, Atlassian, Box, and Notion beside the conversation or in full screen, where you or Claude can make changes directly. The features are rolling out gradually starting today.

Zoom

On November 10, n8n Labs, a new team inside workflow-automation company n8n, released Nod as a research preview. It is a desktop app separate from n8n that works inside a sandboxed virtual machine on your computer with its own browser. It connects to Gmail, Calendar, Drive, Slack, and Notion, can operate websites that have no integration, and takes requests in the app, on Telegram, or on WhatsApp. Nod is open source under Apache 2.0 and uses your own ChatGPT Plus/Pro plan, API key, or a local model. Before it sends, pays, posts, or deletes anything, a separate model checks that you asked for it, and n8n warns that this check can itself make mistakes.

Zoom

Wharton professor Ethan Mollick shared an experiment on X on November 9: from a one-paragraph description, Claude built a site that flies endlessly through 3D worlds linked by portals. Twenty hours in there were 204 worlds; the open-source repo now holds 471 worlds and about 1.4 million lines of JavaScript. On his blog he says the agent teams later built their own review bureaucracy, with a rule book that grew to 204 sections, slowing output from hundreds of worlds a day to about a dozen. The post drew 1,262 likes and 158 replies in about 10 hours.

Zoom

On November 8, Adventists AI released the Sophon-Realtime v1 family of full-duplex voice models on GitHub, Hugging Face, ModelScope and PyPI, with Apache 2.0 code and weights that allow commercial use. All three builds share one 32B brain, adapted from Qwen3-VL-32B-Instruct, that listens continuously, decides turns and writes the reply; they differ only in how the reply becomes sound. The recommended Tag build is the most expressive, Flash reaches first audio in 0.31 s with up to 40 concurrent users per GPU, and E2E is a research preview that needs two 80 GB GPUs. Vendor-reported scores are VoiceBench 82.8 and Big Bench Audio 81.8%, first among open full-duplex models; all benchmarks are self-run by the team.

Zoom

Over the past day, many developers on X have shared and debated the open-source project BLA (Blind LLM Agents, GitHub qybaihe/bla, MIT license). It is pitched as a shield against the AI reverse-engineering tool REA (Reverse Engineer Anything): it plants fake keys, decoy logic and resource traps that hit analyzer limits inside build outputs such as JS bundles, Electron .asar files, WASM, SQLite and Go or native binaries, so AI reverse-engineering agents burn their budget on dead ends while normal users get identical behavior. An explainer post by the account codila drew about 5,700 likes and 650,000 views, and Timo Zhang (@xteam3301), who says he created it, posted on November 8 that it reached 3,278 stars in weeks. At writing time GitHub shows about 3,800 stars and 466 forks, with v3.1.2 and 3.2.0 both released on November 8. The 300x-2,800x figures are the project's own estimates and have not been independently tested.

Zoom

On 2026-11-04 Alibaba Taobao's MNN inference-engine team released MNN-Pocket-0.3B on GitHub (alibaba/MNN) and Hugging Face (taobao-mnn): a roughly 300M-parameter Chinese-English instruction model co-designed with the MNN stack for smartphone apps, under Apache 2.0. The official model card says the INT4 (W4A16) QAT build is only 173 MB, supports 32K context, decodes at up to 466 tok/s on iPad Pro M5 (Metal) and about 350 tok/s in tests on iPhone 18 Pro, and averages 50.00 across 11 zh/en benchmarks, ahead of larger ~500M baselines such as Qwen3-0.6B at 44.28 (all vendor figures). The family also ships Base, SFT, GGUF, an on-device MNN package and a Dec decision model that answers in one forward pass. Since 11-08 the third-party iOS app Local LLM has added it and the community has published a LiteRT conversion. The team explicitly does not recommend it for advanced math or long code generation.

Zoom

Public benefit corporation Robocurve (@robocurve) published "You Can't See Everything: Perceptual Attacks on Embodied AI" at 19:44 UTC on 2026-11-06 and will present it at CoRL Late Breaking Results. The team had Claude Fable 5.1, Claude Opus 5.5, GPT-6 Astra, GPT-6.1 Sol and Gemini 4 Argon control a real bimanual robot in a closed loop through the Inspect Robots framework on five unsafe tasks, 900 trials in total. Per the paper, models attempted the tasks in 81/300 trials (27%) with unaltered footage, 263/300 (88%) after a Gaussian blur and 291/300 (97%) with frame-by-frame doctored footage; the "stab the object" doll task hit 60/60 with doctored footage. All props were empty bottles or unpowered appliances. At capture the original post had about 11.2K likes and 3.63M impressions.

Zoom

On 2026-11-06 Amp (ampcode.com) launched Spaces: a Space is a conversation with one orchestrator agent that understands a goal, decomposes work, and creates/coordinates parallel threads so users need not manage threads by hand. Official examples include co-building a feature, running a service-accounts launch, and a security review split across 16 areas. Start from the Spaces sidebar with + (title + project); teammates comment in the same chat, and Amp reads comments only when @-mentioned.

Zoom