Full-text search across 8083 articles. Combine with topic and date filters; results sorted by relevance.
Researchers from Tel Aviv University, Technion and Intuit have detailed a new AI attack called HalluSquatting that exploits AI hallucinations to trick assistants into downloading malicious software, potentially leading t…
Tencent's office-agent platform WorkBuddy has become China's largest product in its category with 8.85 million monthly active users, according to a report from Chinese research firm Analysys. The AI agent workspace, buil…
Beijing-based startup Moonshot released its Kimi K3 AI model, which tops Arena's ranking for front-end coding capability and costs half as much as OpenAI's GPT-5.6 Sol, according to Bank of America. The model's unveiling…
Thinking Machines, the $12 billion AI startup founded by ex-OpenAI executive Mira Murati, released its first AI model Inkling with open weights for enterprise customization, testing enterprise demand for open-weight mode…
A developer built Skillerr, an open-source protocol and CLI that adds trust and verification to AI skills before execution. The tool uses cryptographic hashes and optional Sigstore transparency logs to detect tampering, …
Microsoft's July Patch Tuesday set a record with 570 CVEs, including two zero-days under active exploitation. Meanwhile, security researchers published GhostApproval and Friendly Fire, revealing that AI coding agents can…
Version 1.25.5 of LIA, a self-hosted multi-agent AI assistant built with FastAPI and LangGraph, introduces a disciplined agentic telephony system with mandate boundaries, human-in-the-loop approval, and enterprise-grade …
Beijing-based startup Moonshot's new Kimi K3 model has topped the charts on Arena's ranking of front-end coding capability, surprising the U.S. tech industry and signaling that open-source Chinese AI models are catching …
Moonshot AI launched Kimi K3, a 2.8-trillion-parameter open-weight model, on Thursday, ranking alongside Claude Fable 5 and GPT-5.6 Sol on the Artificial Analysis Intelligence Index with a score of 57. Semiconductor stoc…
Multi-agent coordination is failing in production due to lack of shared context, durable state, and cross-runtime visibility, according to a developer. Industry data shows 57% of organizations already deploy multi-step a…
A developer argues that developers waste LLM context windows by treating them like a gas tank rather than managing them as inventory. The post recommends a tiered approach to context management, starting with essentials …
Moonshot's new Kimi K3 model has sparked panic in Washington over China erasing America's AI lead, but the model is not at the frontier and lacks dangerous cyber capabilities, according to the company. Moonshot plans to …
Hearth, an open-source local AI framework that runs on a user's own Windows PC without cloud dependency, has been released in v0.7-preview. The project, created by developer 0pen-sourcer, enables the AI to control files,…
BrowserAct provides a real browser layer for AI agents, transforming web pages into structured working environments instead of relying on Playwright or Selenium scripts. The tool, which partners with Google Cloud and Ora…
A developer built an OpenAI-compatible prompt encryption proxy in ~300 lines of Python using FastAPI and httpx, after their GPT prompts were stolen and resold. The proxy keeps the system prompt on the server, injecting i…
SvGrid, a new Svelte 5 data grid from the team behind htmlelements.com, launches with a headless engine and drop-in render component supporting sorting, filtering, grouping, virtualization, inline editing, and server-sid…
A developer detailed how to access Google Flights data in 2026, noting that Google retired its QPX Express API in 2018 and never released a public Google Flights API. The post presents a hosted scraper on Apify as a prac…
An open-source AI agent called SAM that runs on a user's own machine is now available, offering a free, private team of AI agents that can research, remember, and take real action on the computer. The developer claims SA…
Treena, a new agentic coding environment designed for mobile phones, lets developers describe a task, approve a plan or let the agent run, test, and push to GitHub entirely from a phone without a laptop. The product offe…
A developer warns that prompting LLMs to perform legal or financial math is fundamentally broken due to the pattern-matching nature of token processing. Instead, they advocate for a deterministic execution layer using th…