AI Agents news and analysis on Web Pulse: 37986 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
A recursive AI system that builds its own scientific instruments and populates them with hundreds of AI agents distilled several core design principles governing hierarchical metamaterials failure, according to the resea…
OpenAI has committed to creating a formal framework for tracking, investigating, and publicly disclosing consequential cases of model misalignment, covering incidents found during training, evaluation, and deployment. Th…
A student manually classified all 102 apps in the September 12, 2026 F-Droid update batch by how likely an LLM authored them, using repo aesthetics such as commit tone, README emoji density, and the presence of Claude Co…
A developer maintains iOS Agent Skill, an open-source collection of Swift guidance, local references and MCP tools, and the npm package ios-agent-mcp, which bundles Swift review tools, Apple reference retrieval, scaffold…
Proxy-GLS Public (api-public.proxy-gls.de5.net), an API relay tied to the GLS Group logistics company, was flagged as degraded by Uprouter's monitoring probes 16 minutes before publication, with 135ms latency after rough…
L1NK, a short-link tool with QR codes, custom domains and bot-free click analytics, was published to the official MCP registry as version 1.0.0 on 2026-09-17, distributed as a hosted remote over streamable-http and filed…
Version 20.21.2 of io.github.dcostenco/prism-coder, a session-memory server for coding agents distributed as prism-mcp-server on npm, was published to the official MCP registry on 2026-09-17, according to the mcpindex re…
At the AI Infra Summit, AMD argued that AI infrastructure should be designed around adaptability rather than any single chip or fabric, citing three auditable properties — adaptable, economical and open — as the way to p…
Typesafe.ai's Jev is a zero-shot structured-output classifier that runs a single parallel forward pass with no autoregressive decoder, returning one of three typed primitives — Noul (Bernoulli yes/no), Choice (a pick fro…
MindStudio has no one-click importer for Custom GPTs, so converting a Custom GPT requires a manual rebuild in which each Custom GPT feature maps to a MindStudio block, according to a MindStudio conversion guide. The guid…
Markdown has become the default documentation format for AI agent projects, with files like README.md, AGENTS.md, and SKILL.md all using the markup language, according to an analysis of lightweight markup alternatives. T…
OpenAI launched its Data Agent in ChatGPT Work, an internal version of which already serves more than 3,500 OpenAI employees across roughly 70,000 datasets, according to Wren AI's account of the launch Q&A. At the launch…
Firebase AI Logic now runs developer-written Cloud Functions before and after every Gemini generateContent request, per Firebase's Sept. 10, 2026 release note. The beforeGenerateContent and afterGenerateContent triggers …
A practical architecture for scaling a personal AI second brain into a shared team knowledge base keeps each person's personal agent intact and connects it to a centralized, permissioned database rather than building one…
Google researchers and academic collaborators described Dream RSI, a method that lets an AI system improve its own strategy for guiding scientific discovery by simulating past research history rather than running new exp…
An unidentified multimodal AI model called Union Alpha surfaced unannounced on model-routing platforms including OpenRouter with a 262K token context window and no lab claiming it. On a software engineering benchmark sha…
LM Studio, a free desktop application for running local large language models, serves models over an OpenAI-compatible API at http://localhost:1234/v1 and also speaks the Anthropic API, letting Claude Code connect to a l…
Search professionals should prioritize backend software engineering fundamentals and hands-on experience with LLMs, agents, and embeddings, according to a hiring-trends report by Brian Pedersen cited by search consultant…
AMD published a step-by-step FlyDSL workflow for implementing a custom diffusion attention kernel, targeting vLLM's TiDAR (Think in Diffusion, Talk in Autoregression) mode with paged KV caches and scratch storage for spe…
Medusa has built agentic automations, using Claude Code, to handle its release workflow, including drafting release notes, updating documentation, and generating changelog entries, according to a September 17, 2026 compa…