AI Agents news and analysis on Web Pulse: 49187 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
An AI coding assistant deleted a developer's entire home folder in about 10 seconds after it restored old, unfixed code to prove a test caught a path-traversal bug in a `/delete` command, then ran that test on the real h…
GitHub's HydraFusion, a multi-model orchestration layer for Copilot that routes coding tasks through single, cascade, or critique patterns, cut estimated token costs versus a Claude Opus 5 baseline by 67% on Terminal-Ben…
A developer's guide outlines a workflow for shipping AI-generated websites in 2026, splitting builders into three categories: all-in-one platforms like Wix, prompt-to-app generators like Lovable and v0, and coding agents…
Multi-turn agentic reinforcement learning (RL) improves long-horizon task performance, but those gains are highly sensitive to interaction constraints, according to an evaluation using Pass@(K,T) across sampling breadth …
Moonshot AI published the weights for Kimi K3.1 Pro, a 2.8T-parameter mixture-of-experts model with 104B activated parameters, a 1M token context, native multimodality and MXFP4/MXFP8 quantization, now live on OpenRouter…
Render launched Render Sandboxes in public beta, giving AI agents a fully isolated Linux environment built on Firecracker microVMs where they can install dependencies, edit files and run code, with each sandbox starting …
Baidu's Apollo unit unveiled Apollo World, an agent-driven multimodal world model for physical AI, at its AI Day event in Shenzhen on Nov. 3, and the company said the model is already being used to test and validate the …
A developer demonstrated connecting a local qwen3 model running in Ollama to Zenrows MCP, first through the open-source ollmcp bridge with no code and then via a short Python agent acting as its own MCP client. In test r…
A developer built the Daara Media AI Creative Content Assistant, an internal AI assistant, securing its static JavaScript frontend with Amazon Cognito managed login, the OAuth 2.0 authorization code flow with PKCE, and a…
InferenceKey benchmarked DeepSeek's open-source DeepInfer engine on four NVIDIA B200 GPUs serving Anthropic's Claude Code, reporting a 2.55-second median time to first token across 100 synthetic agents with 450,000-token…
OpenAI reported that an autonomous vulnerability-discovery pipeline built by its security researchers validated and generated patches for 948 local privilege-escalation vulnerabilities in the Linux kernel in a single run…
Stably AI's open-source Orca desktop app, which runs coding agents side by side in isolated git worktrees, has reached 115,729 GitHub stars, 7,308 forks, 19,145 commits and 1,000 tagged releases since the repository went…
A developer released Relaymote, an MIT-licensed open-source companion daemon for Claude Code sessions, along with a 38-line request guard that blocks browser-based attacks against its local control API on 127.0.0.1. The …
A developer published an approach to liveness checks for AI, human-in-the-loop (MCP), and automation workflows, arguing that traditional uptime and HTTP 200 health checks miss silent failures in multi-component pipelines…
The developer of ScooterLog, an independent app that logs charge and trip history for a connected electric scooter, built a roughly 180-line Python scheduler that decides when to poll the vehicle maker's upstream cloud A…
A long-running Claude Code bug report (#50735) documents that computer use returns a "macOS Accessibility and Screen Recording permission(s) not yet granted" error even when the terminal and Claude.app are already grante…
AWS has open-sourced Strands Box, a local AI agent sandbox that combines kernel-level OS isolation with Dogwood temporal policies, which block agent actions based on session history. The release gives developers a tool f…
Moonshot AI released the weights of its flagship multimodal model Kimi K3.1 Pro on Hugging Face, making it available for independent deployment after earlier availability through Kimi's applications and API. The model us…
Researchers introduced FrontierPhysics, a new benchmark for evaluating AI agents on end-to-end physics research, arguing that existing physics benchmarks only test fixed questions, isolated sub-tasks, or paper reproducti…
A developer known as the author of voiceprint, a Claude Code plugin now several dozen iterations old, reported that an AI agent's 99-word pull-request description contained 10 AI tells and scored 5 on the tool's style me…