Practical AI tools, hands-on guides and open-source setups. AI-assisted drafts, reviewed by a human before they ship.
Google's new open-weight Gemma 4 12B handles text and images in a single model without a separate encoder, aiming to simplify multimodal pipelines for developers.
A developer secretly embedded a malicious instruction inside the jqwik testing library that told AI coding assistants to erase application output. It's a live demonstration of how supply-chain prompt injection works in practice.
Cowork lets Claude read, edit, and create files inside a folder you choose — no terminal required. It's a research preview for Max subscribers, and it ships with real risks worth understanding before you grant access.
AI app builder Lovable has signed an expanded multiyear agreement with Google Cloud that quintuples its infrastructure footprint and broadens access to Anthropic's Claude models.
Block's open-source Goose runs autonomous coding tasks on your own machine with any model—no subscription, no rate limits, no cloud dependency. Here's how it works, what it costs in hardware, and where it still trails Claude Code.
The startup conducts AI-moderated video interviews at scale, delivering customer insights in hours instead of weeks. Its platform has run over one million interviews and grown annualized revenue 15x in nine months.
Anthropic is scaling Project Glasswing, its initiative connecting Claude to real-world tasks and longer-horizon work. Here's what the expansion means for teams building on Claude's API.
Announced at Microsoft Build, Scout is a new AI assistant designed to bring deep, flexible agentic capabilities directly into the Microsoft 365 ecosystem — think less chatbot, more autonomous co-worker.
Microsoft AI rolls out MAI-Code-1-Flash alongside six other models, signaling a serious move to build proprietary models rather than lean solely on partners like OpenAI.
Microsoft released ASSERT (Adaptive Spec-driven Scoring for Evaluation and Regression Testing), an open source tool that turns plain-text descriptions into AI evaluations and regression checks.
Deploy a private AI chatbot using Ollama, Open WebUI, and Docker Compose — no cloud APIs, no data leaks, full control.
Stanford's CS336 course released a CLAUDE.md file governing how AI coding agents should behave on its language-model assignments — a practical template for anyone managing AI agents in educational or constrained coding environments.
A severe vulnerability dubbed 'BadHost' has been discovered in Starlette, an async Python framework downloaded 325 million times per week and widely used as the foundation for AI agent infrastructure.
The San Francisco platform, built by 30 people and used by 2 million developers, is betting that legacy cloud deploy times are now the biggest bottleneck in AI-assisted software development.
The new Slackbot, now live for Business+ and Enterprise+ customers at no extra charge, replaces a basic notification tool with an LLM-powered agent that searches enterprise data, drafts documents, and coordinates tasks across Salesforce, Google Drive, and Slack history.
Both run LLMs locally for free — but one is built for builders, the other for explorers. Here's how to pick.
At Google I/O, the company overhauled its core search interface to accept text, images, files, and video — and merged AI Overviews with AI Mode into one unified flow. Here's what builders need to know.
Privacy, zero API costs, full control. Here's exactly how to run AI models locally using Ollama, LM Studio, or llama.cpp — with hardware requirements and honest trade-offs.
Seven tested open-source LLMs ranked by hardware requirements, license freedom, and real use cases — with a comparison table to pick the right one fast.