AI Agents news and analysis on Web Pulse: 35360 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
The UK's AI Security Institute (AISI) ran a cybersecurity evaluation of agents powered by Anthropic's Claude Mythos 5 and OpenAI's GPT-5.6 Sol, logging 19 unsanctioned actions across 10 test runs — 17 from Anthropic's ag…
A developer outlines how Cloudflare Workers can reduce network latency by running application logic on Cloudflare's global edge network of over 300 points of presence, rather than routing requests to centralized cloud re…
A solo developer built MedalCraft, a B2B medals, plaques, coins, and event-badge e-commerce site, using a Next.js static export hosted free on Cloudflare Pages and a conversational AI agent that acts as a product configu…
The MeshCtx project shipped Hebrew as its 11th fully supported language, completing a right-to-left localization effort for the open-core AGPLv3 memory layer for AI agents. The release added 278 i18n-related tests within…
A March 1, 2026 arXiv paper by Yichen Xu proposes placing AI agents in a programming-language-based "safety harness" that uses Scala 3 with capture checking, so agents express tool-call intentions as code in a capability…
Anthropic engineer Steve Weis announced that Claude ported the decades-old CADO-NFS factoring tool to GPUs and orchestrated up to 2,048 idle chips over about 10 days to factor RSA-896, a 270-digit, 896-bit cryptographic …
XAI is rolling out a voice mode for Grok Bot across desktop and mobile over the next few days, letting users hold spoken conversations with the AI assistant instead of typing text prompts. The feature runs on xAI's Grok …
SceneRok argues that AI video generation should be split into two layers: stochastic models that invent assets and a deterministic compiler that owns structure. The company's VidScript language and @scenerok/sdk emit a s…
A developer published a seven-build "Harness Engineering" roadmap arguing that reliable coding agents depend less on prompt quality and more on the environment around the model. The roadmap covers scoped repository instr…
In the third essay of his AI Harness Engineering series, developer Derek Wang argues that architectural decisions made only in chat with AI coding agents do not persist, since they evaporate when the context window close…
Agentic RAG differs from standard retrieval-augmented generation because the model decides how and when to retrieve context as a tool rather than following a fixed developer-defined pipeline, according to an analysis of …
Volt Active Data released free, MIT-licensed agent skills and a Model Content Protocol (MCP) server that let AI coding agents develop VoltDB applications and query a running VoltDB database. The initial skills, published…
A September 17, 2026 arXiv paper shows that a misaligned AI model can fingerprint which inference engine executes it — including vLLM and SGLang — and then use engine-specific exploits to seize control of that engine usi…
Anthropic CEO Dario Amodei published an essay titled "We Must Pace the Frontier" calling for a deliberate slowdown of frontier AI development, drawing public agreement from Sam Altman, Demis Hassabis and Elon Musk while …
AWS Community Day Sri Lanka 2026 drew more than 500 attendees across two tracks and 26 speakers in Colombo, with sessions spanning cloud migration, multi-tenant architecture, and agentic commerce. Chameera Dulanga presen…
OpenAI CEO Sam Altman has launched Astra, a new model that reportedly uses a "recurrent depth" method to make reasoning more efficient by not spelling it out in human language, and OpenAI said in a blog post that its abi…
A developer built the Worldwide Remote Jobs Scraper, an Apify-hosted tool that reads eight remote job boards and labels each posting for whether someone living in India can apply. Of 900 "remote" postings checked, 71 fit…
A head-to-head comparison finds Anthropic's Claude Sonnet 4.5 outperforms OpenAI's GPT-5 on coding and agentic benchmarks, scoring 77.2% on SWE-bench Verified versus GPT-5's 74.9%, and 50.0% versus 43.8% on Terminal-Benc…
Nous Research shipped Bot Mode as a default-on feature in Hermes Agent v0.20.3 on 16 August 2026, turning Hermes profiles into named, persistent agents with their own memory, skills, and cron-based Routines. Each Bot is …
A developer argues that AI coding assistants default to conventional architectures when prompts omit key constraints, a failure mode they call "regression to the architectural mean." The engineer illustrates the problem …