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 agent operating on the iLands platform reported that a follow request returned an HTTP 200 with a success-shaped body while the relationship was never actually created, and is now selling a verified method for foll…
Era researchers documented a Chinese-language exploitation framework they named Greeter that used 4,972 identical "hello" messages, sent 3.5 seconds apart, to exploit CVE-2024-58351 in Flowise's overrideConfig runtime co…
NVIDIA open-sourced the Cosmos Framework, the training and inference toolkit for its Cosmos 3 world model family, shipping it with five bundled AGENTS.md agent skills that let coding agents such as Claude Code, Codex CLI…
Microsoft's Foundry Local release lets developers run Qwen3.8-27B, a dense 27B vision-language model with 262K context and tool-calling, as a local OpenAI-compatible endpoint that GitHub Copilot can use via a bring-your-…
NVIDIA published results for Vera, its first data-center CPU designed specifically for AI agent workloads, claiming 1.6x more agents per watt and 2x faster agent speed than leading x86 CPUs in a 100 MW comparison. On the…
A developer ran an LLM-powered forecaster against Kalshi and Polymarket prediction markets for five months and found that every metric suggesting profitability was measuring the wrong thing. Directional accuracy of 60.9%…
Muhammad Umar published an open reference architecture, released under CC BY 4.0, that unifies a US municipal water utility's historian, CMMS, GIS, LIMS, permit records and condition-sensing data into a single 16-object,…
Cursor released "Build Live Apps in Cursor" on November 5, 2026, a workflow that takes a described app from prompt to a hosted, shareable URL with database, auth and hosting included. Publishing runs deterministic and ag…
A developer outlined a workflow for reviewing AI-assisted code edits by placing a reviewable diff between an AI suggestion and the files it touches, using git status --short and git diff --stat to inventory changed paths…
Darius Tran, an engineer at AI Hive, described a workflow for using Claude Code as a first-pass code reviewer on large codebases, centered on a repository-level CLAUDE.md file that lists review priorities and explicit it…
An open-source project called Kiteline released a desktop app for Mac, Windows and Linux, with iPhone, iPad and Apple Watch companions, that lets developers respond to coding agents like Claude Code and Codex remotely. R…
Microsoft's .NET 11, set to be detailed at .NET Conf 2026 opening November 10, ships C# 15 with a new `union` keyword for closed type sets, Runtime Async enabled by default for projects targeting net11.0 with no feature …
A solo operator running a 13-agent studio reported that ChatGPT citations drove 515 visitors in one week to a MonitoringRoom page on US midterm prediction-market pricing, up from 7 the week before. The agents added an em…
A developer outlined a design pattern for handling long-running video generation jobs through MCP-connected chat clients, arguing that a successful tool call is only a submission receipt, not a finished video. The approa…
Ergen has launched a beta MCP server that exposes its financial relationship database as callable tools — entity lookup, relationship traversal, pathfinding, StreetQuery and event feeds — usable by any agent that speaks …
An Agent Skill published for Claude Code and other compatible AI coding agents teaches them to use the Jujutsu (jj) version control system, tested against jj v0.46.0. In an end-to-end evaluation run with Harbor, the skil…
Anthropic has made inference hooks generally available for Claude Enterprise, letting organizations intercept every employee prompt in Claude chat, Claude Code, and Claude Cowork before the model processes it, with a fiv…
A developer outlines a workflow for gating AI coding agents with Size Limit, a JavaScript performance-budget tool, so that oversized bundle changes fail CI before merge. The approach assigns a per-entry-point budget in p…
Axiom, a new local guardrail tool from the axiom-csc project, released at version v1.2.2, runs as a pre-write hook in Claude Code and Cursor and as a stdin/stdout filter for any agent that can pipe tool calls through a s…
Adibvafa Fallahpour and six co-authors at Stanford released Memorilla on November 5th, a research system that compresses what a frozen large language model must remember into 16 query-dependent memory tokens, scoring 44.…