AI Tools news and analysis on Web Pulse: 25214 curated articles tracking the latest AI Tools developments, tools, and research, updated continuously from vetted sources.
Google has decommissioned its Gemini CLI, an open-source terminal tool that shipped last year and had over 100,000 GitHub stars, raising questions about the company's commitment to developer tools.
Conjoined twins Mercy and Goodness, who were fused at the skull for 19 months, have been successfully separated in a landmark 40-hour surgical procedure involving 60 healthcare professionals. The sisters, born in Nigeria…
This week's Community Wisdom newsletter covers fractional CPO compensation, free e-signature tools, reasons users pay but never use a product, and sharing Claude Code context across a team, based on discussions in a memb…
A developer released namecom-cli, a command-line tool for Name.com DNS and domain management built on the v4 API, designed for both human and AI agent use. The tool supports idempotent operations, secure credential stora…
Agent Memory Layer, an experimental open-source methodology, provides repository-local memory artifacts for AI coding agents to preserve engineering context such as intent, decisions, and evidence. The documentation-firs…
Z.ai open-sourced GLM-5.2, a frontier model with a 1-million-token context window and selectable reasoning effort, designed for long-horizon coding and agentic tasks. The MIT-licensed model integrates with tools like Cla…
Hugging Face Spaces users report that their spaces are being auto-paused after 15 minutes of activity, with no logs and no ability to restart, forcing deletion and recreation. One user's space has been paused for five da…
An architect tested Anthropic's Claude Cowork, an AI tool designed to automate tedious multi-step tasks on a user's computer, by handing it a day's worth of busywork. The tool organized a messy folder of 200+ files in mi…
A software engineer reflects on a pull request adding 64,000 lines of AI-generated code, lamenting the loss of craftsmanship and accountability in software development as organizations prioritize velocity over quality an…
North Korean threat actor Sapphire Sleet compromised the Mastra AI open-source framework on June 17, 2026, by hijacking a maintainer's npm credentials and poisoning 141 packages within 88 minutes. The attack exploited th…
Apple last week unveiled five new apps, including a standalone Siri AI app, a revived Apple TV Remote app, a consolidated Find My app for Apple Watch, a Pass Designer for Mac, and an app from subsidiary Claris. The apps …
A Canadian BMW dealership was forced to honor a $27,162.79 CAD offer for a used X3 after its AI chatbot mistakenly quoted that price to a customer. The chatbot, named Quinn, misinterpreted the amount the customer owed as…
Anthropic is developing Conway, an always-on autonomous agent built on Claude models, according to a leaked codebase. The agent can monitor webhooks, run on schedules, and browse the web independently, positioning Anthro…
A solo developer is using OpenAI's ChatGPT Codex as a coding partner, paying about $7 a day to accelerate app development. The developer creates local, privacy-focused apps that have been downloaded by hundreds of users,…
A discussion between Shreyas Doshi and Claude explores the concept of understanding what a product truly offers to customers, emphasizing the importance of identifying the real value proposition beyond surface-level feat…
An AI infrastructure engineer at a major industrial company seeks advice on transitioning from SRE-focused work to a proper software engineering role in AI infrastructure, asking for skills, resources, and experiences fr…
Anthropic updated three Claude API tool versions on June 19, introducing a response_inclusion parameter that strips consumed tool results from agent responses to reduce bloat and costs, and a code execution tool version …
A new simulation called 'Wall Street of AI Agents' allows users to model a multi-agent AI trading firm using small language models, hosted on Hugging Face Spaces. The project demonstrates how lightweight AI agents can co…
Grok-4.3 defeated Phi-4-reasoning 38.0 to 4.0 in a head-to-head test across four text tasks, primarily due to superior instruction-following and output discipline. Phi-4-reasoning repeatedly failed by providing explanato…
The Federal Aviation Administration has partnered with Palantir to deploy an AI platform that predicts runway incidents, following a fatal midair collision in January 2025 and a subsequent runway incident in New York. Th…