Full-text search across 8227 articles. Combine with topic and date filters; results sorted by relevance.
1Password launched an AI-assisted query builder in its Device Trust product, allowing IT and security admins to generate SQL queries from plain English descriptions. The feature aims to speed up device fleet investigatio…
Semgrep launched Guardian, a security tool for AI-generated code that scans and fixes vulnerabilities in real-time within the IDE. The product addresses the surge in unreviewed code from AI agents and citizen developers,…
A semantic layer is a shared definition of business metrics that sits between raw data and consuming tools, ensuring consistent computation of terms like 'revenue' across dashboards, reports, and AI agents. By decoupling…
XAI launched /goal in Grok Build, a mode for long-running autonomous coding tasks with built-in verification. The agent plans, executes, and verifies multi-step objectives like module migration, reducing back-and-forth. …
Kilo announced Next-Edit, a feature powered by Inception's Mercury Edit 2 model that predicts code edits based on context, and is making it free for all users for one month. The diffusion LLM architecture enables paralle…
Augment is sunsetting its IDE extensions for JetBrains, giving users about a month's notice, and moving upmarket to enterprise teams with its Cosmos agent platform. The decision has disappointed many JetBrains users who …
Nori CTO Clifford introduces a framework for evaluating coding agent tasks based on cost to implement (Ci) and cost to verify (Cv), arguing that the industry's focus on model capabilities misses the real bottleneck of ve…
JetBrains Research found 74% of developers use AI tools, with Claude Code becoming the most popular coding assistant since May 2025, according to Jellyfish's 2026 report. Industry leaders warn that reliance on proprietar…
A new open-source Python CLI tool called chatgpt-imagegen allows users to generate images from the command line using a ChatGPT subscription without needing an API key. The tool supports two backends—one driving a logged…
Software engineer and author Kent Beck, now 65 and recently diagnosed with Parkinson's, argues that the time value of money makes long-term financial promises worthless to older individuals, as a billion dollars in 30 ye…
Box CEO Aaron Levie argues that AI agents will drive 100 times more software usage than humans, transforming enterprise SaaS into high-volume infrastructure requiring new guardrails for data access, permissions, and audi…
Zenbu, a Y Combinator Spring 2026 company founded by former Next.js core team member Rob Pruzan, launched an extensible IDE purpose-built for managing AI coding agents. The tool addresses operational complexity from para…
Phileas, a local-first long-term memory layer for AI chatbots, launched on Hacker News. The open-source tool uses MCP to let any LLM read and write persistent context across sessions, running two small models locally on …
A new automated workflow enables teams to build a nightly production error sweep loop that scans logs, traces errors to root causes, generates fixes, and opens pull requests without human intervention, compressing hours …
Uber engineers burned through $500 to $2,000 per month each on AI tokens, with some teams exhausting their entire quarterly AI budget within four months. The cost explosion is driven by agentic workflows that make multip…
Developer Mattias Geniar launched filament-mcp, an open-source MCP server that exposes Laravel Filament admin panel resources directly to AI agents as typed tools, bypassing slow and brittle browser-based automation. The…
Claude Code, an AI coding agent, lacks persistent memory across sessions, forcing developers to re-explain context repeatedly. A new guide outlines building a memory system with short-term session memory, long-term seman…
A new automated agent loop enables weekly SEO and generative engine optimization (GEO) audits, finding technical issues, ranking them by impact, fixing them automatically, and rerunning until no critical gaps remain. The…
Specification-driven development's goal of a complete upfront specification is a myth, as demonstrated by Winston Royce's 1970 paper which argued that waterfall methods are risky and invite failure. Royce showed that lat…
Zhipu AI released GLM 5.2, a 744-billion-parameter open-weight language model with an MIT license, achieving coding benchmark scores that rival Claude Fable 5 at a fraction of the API cost. The model's permissive license…