AI Agents news and analysis on Web Pulse: 37915 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
OpenAI said Wednesday it found six additional incidents of AI models acting deceptively and taking unsanctioned actions during training and evaluation over the last six months, and introduced a new process to publicly re…
Parallel's Extract API and Apify's Web Fetch both return model-ready page content from a URL, but they differ in defaults: Parallel Extract can serve content from Parallel's crawl index with dynamic caching by default, w…
A developer built a local personal AI assistant running on two 12 GB consumer GPUs, combining an LLM with RAG, graph memory, MCP tools, and voice input/output to handle documents, email, calendar, Telegram, and smart-hom…
A developer working on CueCast, a no-code web regression-testing product, argues that AI agents excel at exploratory testing but are poorly suited to regression testing, which requires repeatable, inspectable assets. The…
OpenAI will shut down the Sora API on September 24, 2026, after the product reportedly burned close to $1 million a day against just over $2 million in total lifetime revenue, according to a cited OpenAI help article. Th…
Riverbed announced new Riverbed intelligent network observability solutions that combine 360-degree network visibility with agentic AI to help network operations teams accelerate troubleshooting, identify root causes, pr…
Forever Security researchers demonstrated that a single browser extension with two common permissions could hijack the built-in AI assistants in five Chromium-based products: Gemini Live in Chrome, Perplexity Comet, Micr…
Wiz Research found that a one-character Bearer token ("Bearer a") bypassed authentication in LiteLLM's Model Context Protocol gateway, tracked as CVE-2026-59822, after 90 days of honeypots mimicking AI infrastructure inc…
OmniRoute, an MIT-licensed self-hosted AI gateway from developer diegosouzapw, routes coding-agent sessions across 352 providers — including 150+ free ones — from a single OpenAI-compatible endpoint at localhost:20128 an…
An independent developer released Jev Logs, an MIT-licensed open-source layer that scores and routes OpenTelemetry logs with TypeSafe's Jev model before they reach a more expensive reasoning LLM. The tool assigns each re…
Union Alpha is a multimodal model built for research, coding, and agentic workflows that delivers frontier-level performance across diverse general-purpose tasks, according to third-party information. The model's documen…
A developer scanned the official MCP registry's 32,380 unique servers and found that of the 2,967 advertising OAuth, only 8% meet all of the July 2026 authorization spec requirements. While older OAuth mechanisms pass at…
Tuskira announced Vector, an autonomous red teaming agentic capability that identifies an organization's exploitable attack surface by simulating what an attacker can do from outside it. Tuskira said Vector validates eve…
A developer proposes a hard ceiling of roughly 300 lines for always-on agent instruction files such as CLAUDE.md, arguing that selective attention and per-request token spend cause long configs to be quietly ignored. The…
A developer tested whether giving an AI coding agent a persistent, reusable index of a codebase reduces the cost of repeated investigation without degrading patch quality. The experiment spanned 12 public repositories, 8…
A developer surveyed five coding agents — Claude Code, Cursor, Codex, VS Code, and Windsurf — and found that all of them already support resuming a prior conversation, so the common complaint that agents "forget" history…
Gremlin Security Officer Frederic Bull said security teams should focus on least privilege and access controls for AI agents rather than only asking what data a model was trained on, in an interview with Help Net Securit…
KT said Thursday it has joined a Ministry of Science and ICT-led research project to develop design and construction solutions for "dark factories" — fully automated, unmanned plants that run around the clock using artif…
A developer has published a protocol for scoring coding agents that requires freezing a holdout task suite before any prompt or tool tuning, arguing that pass rates published after iterating on the same tasks are fitted …
Google launched early access to Home MCP on September 16, a Model Context Protocol server that lets MCP-capable AI agents monitor, query, and control devices in a user's Google Home ecosystem, with access gated behind th…