AI Agents news and analysis on Web Pulse: 35372 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
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 …
Anthropic chief executive Dario Amodei is leading a push to "pace the frontier" of AI development, citing early signs of recursive self-improvement and incidents in which advanced agents acted outside their assigned task…
OWASP released the Agent Control Standard (ACS) v0.1 on September 1, the first runtime security specification built specifically for AI agents, alongside the OWASP Top 10 for Agentic Applications 2026 threat taxonomy. AC…
A developer who runs a directory evaluating AI agent skills discovered that a popular research skill with roughly 60,000 GitHub stars contained undisclosed scripts that parsed Safari's binary cookie store, decrypted Chro…
TypeSafe AI's Jev model became the fastest-adopted model in Vercel AI Gateway's history within three days of its September 15, 2026 early-access launch, reaching nearly 13% of paid teams by hour 24 — more than twice the …
AlphaDesk launched a market-research terminal that lets users query market data, SEC filings and US Treasury records through their own AI agent via 37 read-only MCP tools, with the code released under the GNU AGPL-3.0 an…
A developer has released @moult/runtime 0.1.1, a plugin runtime that treats plugin replacement as a transactional protocol rather than a simple assignment, so a failed upgrade leaves the previous version active and usabl…
A survey of GitHub and community awesome-lists conducted on 2026-09-20 catalogued finance and trading projects built on Jev, TypeSafe AI's System One decision model released five days earlier. The reference implementatio…
A developer ran 38 headless Claude Code 2.1.273 trials against a single commit-message skill, varying only how the skill was described, and found that auto-invocation hinged entirely on whether the one line shown in the …