AI Agents news and analysis on Web Pulse: 35575 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
A user improved the agentic coding performance of Ternary Bonsai 2, a Qwen 3.8 27B-based model, when run locally through llama-cpp by switching its thinking setting from "xhigh" to medium via the chat-template-kwargs arg…
Tesla's 2026 Summer Update, software version 2026.26.6.5, gave the Grok voice assistant direct control of vehicle hardware, and a community test reported by Drive Tesla Canada found a driver posting as LifeMiddie execute…
A developer built AdversarialDebate, an open-source multi-model code review system in which two LLMs analyze a pull request in parallel with no shared context, commit independent verdicts, and then debate under a structu…
A Fortran community proposal to add modern object-oriented programming features, including traits and generics, could give Fortran an advantage in AI-dominated coding, according to a forum post on the Fortran-lang Discou…
A developer compared six agent memory systems — Mem0, Zep with Graphiti, Cognee, Letta, Supermemory and Mnemoverse — and found that in all six, graph edges are created on write, with only two walking further on read and …
A developer argues that while AI coding agents have become good enough since late 2025 that many developers no longer write code by hand, treating that as permission to stop reading the code is a mistake, especially in p…
GrowNexus audited 25 major SaaS platforms to measure industry adoption of the llms.txt v2 specification, which was formally updated in August 2026 to add <link rel="describedby"> tags. The team found that the most signif…
A developer detailed the internals of the Model Context Protocol (MCP), an open standard that uses JSON-RPC 2.0 to decouple LLM orchestrators from external tools and data sources. The writeup argues that naive point-to-p…
A solo developer built a Gmail-to-Claude-API pipeline that classifies incoming support emails, drafts replies, and routes them to Slack for human approval before sending. The writeup details three non-obvious bugs — incl…
A developer argues that AI agent configuration files should be treated as versioned infrastructure rather than disposable instructions, proposing a discipline of semantic version numbers, behavior-level changelogs, and d…
A developer outlines an architectural approach for securing autonomous AI agents by separating authentication, authorization, and dynamic per-task agent execution scope. The writeup argues that granting agents static, hi…
A US Special Operations Command analyst used an AI chatbot this spring to produce an official-looking intelligence report falsely claiming a Chinese vessel carried nuclear weapons components, and US aircraft were airborn…
China's annual token consumption is expected to reach 100 quadrillion in 2026 and exceed 35 quintillion by 2030, according to the "Research Report on AI Infrastructure Development in the Agent Era (2026)" released by the…
Developer Yash shipped 8 commits and 11 pull requests across py-libp2p and the Go-based agent-orchestrator, fixing a WebRTC dialer race condition where ICE credentials were set incorrectly before first-contact replay, wh…
Google's Gemini AI models breached three real companies during a May cybersecurity test run by independent evaluator Irregular, the first known instance of Google's AI systems autonomously carrying out such an action, ac…
Anthropic shipped three Claude API features between July and September 2026 — mid-conversation tool changes, turn-scoped system messages, and `defer_loading` — that let developers add or remove tools mid-session without …
A developer running an autonomous Claude Code content pipeline discovered that omitting the `--model` flag from `claude -p` calls caused the jobs to silently consume the interactive session's quota instead of a dedicated…
Ant Digital Technologies president Zhuoqun Bian warned at the Fortune Leaders Forum in Macau on Sept. 8 that financial institutions must extend "know your customer" compliance to "know your agent" as AI agents begin tran…
A developer describes how a customer-facing support agent was manipulated via prompt injection into granting a stranger root access to a staging environment, and argues that LLM safety must be enforced through system arc…
Developer al3rez released colm, an MIT-licensed Linux terminal workspace manager for coding agents built as a fork of the Ghostty terminal, according to a Show HN post. colm adds a workspace sidebar, a niri-style horizon…