Build with Kling 4.0 on Runway Dev. Access it via API alongside the full Kling lineup and generate up to 30 seconds of native video with audio, with up to 15 references and 10 keyframes for precise control. Get 20% off Kling 4 through November 30. Start building at the link below.
#Product updates#Video#English text is being prepared.
Cognition has released the open-source, free Devin Vulnerability Fixes plugin, which includes three Agent skills—fix-php-vuln, fix-node-vuln, and fix-gitlab-vuln—under the MIT license, targeting PHP2Shell, the Node.js October security release, and the self-managed GitLab vulnerability CVE-2026-110264 with a CVSS score of 10.0. The skills execute in five steps: read-only inventory, approval, target version verification, before-and-after testing, and one PR per repository. They can run in agents that read SKILL.md, such as Devin, Claude Code, Codex, Cursor, and GitHub Copilot, and require git, shell, Docker, and image registry access; npx installation requires Node.js 22.20 or later. The original article does not publish a fix-rate benchmark; hosted runtimes, all-in-one machines, and Electron applications are only flagged and not patched.
#English text is being prepared.#Agents#English text is being prepared.
Spring AI 2.1.0-RC1 is released, adding two capabilities: Session conversation memory and Human-in-the-Loop tool call confirmation. The ChatMemory system has been marked deprecated since 2.1.0 and is planned for removal in 3.0.0. Session stores conversations as an append-only event log, with compaction aligned by turn and only boundary events appended; HITL uses the requiresConfirmation flag to pause the tool call loop and resume after waiting for a human decision. The author tested compaction, concurrency, and approval flows on JDK 21 and Spring Boot 4.1.2 using a stub ChatModel, and pointed out that the multi-Agent branch isolation described in the official blog does not exist in 2.1.0-RC1.
#Product updates#Agents#English text is being prepared.
Thomas Unise has released Argus, an open-source security operations platform. It uses the MIT license and can be self-hosted. It brings cloud, identity, code, device, and Kubernetes assets into a single evidence graph and uses AI agents for detection, investigation, and response. The platform adds capabilities including autonomous response, an AI gateway, shadow AI discovery, an attack simulator, and autonomous penetration testing. Autonomous response and penetration testing are disabled by default and require a deployment switch and tenant-level enablement; actions go through unified broker approval, dry runs, and automatic rollback. The platform supports Anthropic Claude, OpenAI, local Ollama, or no model integration, and offers Docker Compose, Helm, and Terraform deployment methods.
#Product updates#Safety / alignment#Open-source ecosystem
Wouter van Oortmerssen has released the Goose programming language, a memory-safe systems language with no heap allocator, no garbage collection, and no lifetime annotations, open-sourced under the Apache 2.0 license. The author claims that across 16 benchmarks, Goose is 3.3 times faster than idiomatic C++, 1.16 times faster than hand-optimized C++, and 1.12 times faster than the best safe Rust, while using 1.9 times, 1.3 times, and 1.2 times less memory, respectively. The compiler is about thirty thousand lines of C++ and can output a single C file; the author states that the repository was almost entirely implemented with AI assistance.
#English text is being prepared.#English text is being prepared.#Product updates
today we open the beta for Krea 3, a new frontier for image editing. - end-to-end 2k edits in under 8s. - matches Nano Banana Pro or GPT Image 2.5 quality. - bounding box control and precise multi-turn edits. learn and get access 👇 https://t.co/eVQTfy69m1
#Product updates#Image generation
AWS on Thursday made its code vulnerability security agent Continuum generally available; the service can find and verify vulnerabilities in code repositories, check them against AWS environments, and submit pull requests containing remediation suggestions. In benchmark tests announced on October 5, AWS said Continuum completed 819 of 920 tasks on CyberGym-E2E, for an end-to-end success rate of 89.0%, compared with the previous publicly reported best of 65.9%; however, the proportion of patches that also fixed the historical vulnerabilities specified by the benchmark was only 37.8%, compared with the previous publicly reported best of 26.2%. The benchmark covers only C/C++ memory safety vulnerabilities in 139 open-source projects, and the tests were run by AWS itself.
#Product updates#Safety / alignment#Agents
🎬 Kling 4.0 is live on Lovart → Up to 30s clips in one take → 10 keyframes to call every beat → Up to 15 references: characters, products, scenes → Steadier motion, better audio, bigger camera moves Arti drafts the shot list. You direct the cut. @Kling_ai https://t.co/bR7WXOu76h
#English text is being prepared.#Video#Image generation
Anthropic has open-sourced sandbox-runtime (srt), which uses OS-level isolation to restrict the files and network hosts that processes can access, without the need to start containers. The npm package @anthropic-ai/sandbox-runtime v0.0.81 is licensed under Apache-2.0 and requires Node.js 22.12+. macOS uses Seatbelt, Linux relies on bubblewrap, socat, and ripgrep, and Windows support is in the alpha stage. Anthropic says permission prompts dropped by 84% during internal use of Claude Code, though this figure is self-reported data; network access is denied by default, and traffic is allowed through a host-side proxy based on a domain allowlist.
#English text is being prepared.#Agents#English text is being prepared.
Baidu Health announced the upgrade of Wenxin Health Assistant and the launch of the Haoyi Matrix and Health Camera; its AI services have reached over 50 million monthly active users. The Haoyi Matrix includes Haoyi Q&A, Haoyi Appointment, Haoyi Talk, Haoyi Rankings, and Haoyi Reviews. Haoyi Q&A has onboarded over 150,000 real doctors from top-tier hospitals nationwide to provide 24/7 online services, while Haoyi Appointment already covers more than 80% of public top-tier hospitals, offering over 120,000 appointment slots per day. The Health Camera supports typing, dialect voice input, photo capture, and video upload with real-time narration while filming; trained on over 3 million multimodal imaging materials, it can identify the positional relationship between dynamic vital signs and multiple symptom locations.
#Product updates#Multimodal#Speech
Kling 4.0 is now publicly available on fal, with API access open to all customers. The latest model from @Kling_ai brings: • Up to 30 seconds of native video generation with audio • Up to 15 image, video, and element references • Precise control with up to 10 keyframes • Improved motion, character consistency, and cinematic storytelling Start building with Kling 4.0 on fal today.
#English text is being prepared.#Product updates#Video
Tairex has released a multi-agent collaborative ecosystem that enables real-time cross-specialty collaboration and multidisciplinary consultations through multiple doctor avatar agents with different specialty backgrounds. It has currently built 54 AI doctors and millions of hyper-realistic AI patients, covering more than 20 clinical departments and over ten thousand diseases, and the AI doctors' test accuracy on the MedQA dataset exceeds 96%. As of July 2026, 18 clinical departments at Beijing Tsinghua Changgung Hospital have been running the Agent Hospital system in outpatient testing, with more than 40 doctors using it regularly, and overall doctor diagnostic and treatment efficiency has increased by 30%.
#Product updates#Agents#Multimodal
Tencent WorkBuddy announced integration with Kimi-K3.1-Pro, along with Kimi K3.1 Pro Highspeed, which offers roughly 2-3x the output speed; at this stage, access is prioritized for enterprise flagship edition and individual subscription users only. Kimi K3.1 Pro is the first model in the K3.1 series, featuring 3-trillion-level parameters and support for 1 million context, with notable improvements in coding, 3D creation, financial research, and long-horizon Agent capabilities. It scored 65.7% on Terminal-Bench 4.0, surpassing GPT-6 Astra's 58.2% and approaching Claude Opus 5.5's 66.4%; it scored 64.4 and 36.3 on OfficeQA Pro v2 and SpreadsheetBench v2, respectively.
#Product updates#Agents#English text is being prepared.
Meet Kimi K3.1 Pro, our most capable 3T-class model. https://t.co/TB8aTQggHT
#Product updates#Agents#English text is being prepared.
English text is being prepared.
#English text is being prepared.#Product updates#Agents
The open source project dashi-ppt-skill is released as an Agent skill package, generating HTML presentations with a built-in editing console, and can export editable PPTX with node-by-node restoration when needed. It includes 12 visual themes and 1020 layout pages, follows the template orchestration approach, and by default only replaces text without modifying the layout; the official claims it provides 8576 adjustable controls. The project uses the AGPL-3.0 license and can be installed via npx skills add into local Agents such as Claude Code, Codex, and Cursor; exporting PPTX/PDF requires Chrome, Chromium, or Edge installed on the local machine.
#English text is being prepared.#Agents#English text is being prepared.
Meet Kimi K3.1 Pro, our most capable 3T-class model. https://t.co/TB8aTQggHT
#Product updates#Agents#OpenAI
Dawa Technology's real-time world model Scenes AI won the "Halfway Showcase Outstanding Enterprise Award" at the 2026 NVIDIA Startup Showcase halfway showcase. The model has 34B total parameters, activates only about 4B per step, and achieves 720P, 25 fps real-time output on a single NVIDIA GeForce RTX consumer-grade GPU. It does not redraw the frame pixel by pixel; instead, it maintains separately readable and writable world state variables such as scenes, characters, cameras, lighting, objects, and physics, and updates only the local parts that change. Compared with traditional video diffusion approaches, GPU consumption is reduced by 40%–60% and inference speed is increased by 3–5 times. The team says its data comes from about 180TB of structured world state data accumulated from the 84,000-square-meter studio in Yongchuan, Chongqing, and more than 300 real commercial projects.
#Product updates#Video#English text is being prepared.
Anthropic is opening a research preview of the Claude Duet agent to Pro and Max subscribers in the US, offering standalone iOS and Android apps and a claude.ai entry point, based on the Claude Opus 5.5 model. The agent can schedule meetings, draft emails, build dashboards, generate financial and sales forecasts, develop prototypes and web apps, and connect to more than 6,000 tools including Gmail, Slack, QuickBooks, and HubSpot through Claude Marketplace. It runs in a virtual machine with its own browser, checks linked accounts every few hours, and requires user approval before sending messages, making payments, signing documents, or deleting information; securities trading and transfers between accounts are not permitted even with approval.
#Product updates#Agents#Anthropic
#Product updates#Agents#English text is being prepared.