Full-text search across 33725 articles. Combine with topic and date filters; results sorted by relevance.
Stacktree has introduced an MCP server that gives AI coding agents a "publish" command for HTML files, generating private, unguessable URLs instead of requiring full deployment. The tool, available via a single `npx stac…
Meta has embedded facial recognition code, internally called "NameTag," into the Meta AI smartphone app used by its smart glasses, according to investigations by Wired and the Electronic Frontier Foundation confirmed Thu…
Anthropic reports that its AI model Claude now generates over 90% of the company’s production code, with engineers shipping eight times more code daily than in 2024. The company is advocating for a verifiable, global pau…
Meta has quietly embedded face-recognition code for its smart glasses into the Meta AI app, which has been downloaded over 50 million times, according to a WIRED analysis. The feature, internally called "NameTag," identi…
E2B has launched a special offer for founders in a16z Speedrun, providing Andreessen Horowitz-backed early-stage teams with access to its isolated code execution sandbox infrastructure for AI agents. The infrastructure a…
A developer built a tool called ClaudeActivity that parses Claude Code session logs and generates visual HTML reports. The tool reveals repository traversal patterns, edited files, session heatmaps, coding personas, toke…
A new study introduces "handoff debt," the rediscovery cost incurred when a coding agent resumes an interrupted task left by another agent or engineer. Testing across 75 source tasks and 724 takeover runs per model, rese…
Nexusyn has introduced a time-aware memory API that integrates with AI agents via the Model Context Protocol (MCP), enabling persistent memory across sessions without custom glue code. The API provides `add_memory` and `…
SharkBay, a new macOS workbench for managing multiple AI coding agents, launched as an open-source tool that lets developers run Claude Code, Codex, Gemini, and other agents from a single workspace. The application provi…
Ali, CEO of Velork, launched an AI-powered integrated development environment (IDE) that converts website designs and Figma files directly into clean code. The tool, built on VS Code, features a Canvas tab that allows AI…
A developer built a local MCP server that provides Claude Code with real PR context, including blame history, linked issues, and structured review formats. The tool reduces PR review time from 90 seconds to 33 seconds by…
Cognition, the developer of the autonomous AI coding agent Devin, raised over $1 billion at a $25 billion pre-money valuation on Wednesday, a sharp increase from its $10.2 billion post-money valuation eight months ago. T…
MartinLoop, an open-source control plane for AI coding agents, introduces hard budget stops, JSONL run records, and verify-gated completion to enforce accountability in autonomous coding workflows. The project was develo…
A developer created Agent Launch, a unified command-line interface that provides a consistent workflow for seven different local coding agents including Codex, Claude Code, and Cursor Agent. The tool, accessed via the si…
Anthropic is preparing to release Mythos 1, a preview model labeled "claude-mythos-1-preview," for integration into Claude Code and Claude Security, marking a shift from earlier plans to keep the model restricted. New so…
Datrix is a no-code chat interface that allows users to upload datasets and receive interactive charts and trained machine learning models by asking questions in plain English, with Gemma 4 handling all Python code gener…
Venture capitalist Marc Andreessen told Joe Rogan that AI coding agents are superior to human employees because they never get drunk, sick, or file HR complaints, and they work 24/7 without emotional frustration. He desc…
ShadowCat is a fully offline, single-file HTML page that enables data transfer between two devices by encoding files into a sequence of QR codes, designed for old phones with working cameras and browsers but non-function…
According to a study by CloudBees, the use of AI-generated code is leading to an increase in production failures and higher spending. The research highlights a significant "verification gap," indicating that organization…
ClawBattle, a new open-source benchmark that tests multimodal LLMs on code golfing tasks, which require both visual and textual understanding. It claims the benchmark avoids data contamination by using confidential, top-…