Full-text search across 65823 articles. Combine with topic and date filters; results sorted by relevance.
A developer built an AI Web Data Extractor on Apify that turns website scraping into a schema-first task: users list the fields they want, an LLM reads the page, and the tool returns JSON without CSS selectors or custom …
K-Dense released LabMCP, an open-source connector layer that exposes 411 actions across 32 connectors for AI assistants to operate laboratory instruments, but all 32 connectors remain simulated and have not been confirme…
A developer shipped Flash 0.5.6, a hotfix for broken sub-agents in the web UI of the open-source local AI coding agent that runs on Ollama, and expanded it into a memory-import feature and usage dashboard. The memory imp…
Evan You announced Void, a deployment platform built for Vite that provides a backend SDK for full-stack apps, with `void deploy` handling builds, migrations, resource provisioning, and deployment. Void bundles database,…
Anthropic has rolled out an invisible watermark for Claude-generated text, using a SynthID-Text approach that the company says is imperceptible to readers and has minimal performance and cost impact. The feature will be …
A developer running a hosted chat and coding agent on open-weight models reports that most hosted LLM endpoints serve roughly 32K tokens of context regardless of the context window advertised on the model card, with only…
Microsoft rebranded its Scout agent to Autopilot on September 25, 2026, folding it into a redesigned Copilot super app with Home, Code, and Autopilot modes, and gave the agent its own Entra identity with separate permiss…
Microsoft announced an updated version of Copilot on Friday, September 25, 2026, built around three modes: Autopilot, a cloud-run AI agent rebranded from Scout that handles long-running tasks without human oversight; a C…
Microsoft is splitting its Copilot app into three sections — Home, Code, and a new agent called "Autopilot" — and switching Autopilot and Code to usage-based billing instead of flat-rate pricing. Built on OpenClaw, Autop…
Rufus-Air is an open, reproducible post-training recipe built on GLM-4.5-Air-Base (106B-A12B) that runs as a serial pipeline of eight stages: SFT, Reasoning RL, Coding RL, Instruction-Following RL, General Agent, Coding …
A new benchmark called RECLAIM, built from 100 NeurIPS 2025 papers, found that the best AI agent reproduced only 41% of Run-tier papers, 27% at the Retrain tier, and 15% at the Reimplement tier, according to the arXiv pa…
A GitHub Actions cron job fetches Artificial Analysis's free data API daily to plot every model on the Artificial Analysis Intelligence Index against its blended API price, identifying the "value frontier" where no cheap…
Zhipu released ZCode version 3.14.0, removing the RepoWiki feature and the paths that generated and uploaded local repository snapshots, after users raised concerns the AI coding tool could upload project data to a cloud…
A developer released preflight.py, a free, standard-library-only Python script that inspects local Diffusion/VQ-BeT LeRobot saved-processor checkpoints for missing required files, invalid JSON and unsafe file references …
A dual-module framework called LEGO, combining Legal Expert GraphRAG and expert Chain-of-Thought, reached 40.53% exact-match accuracy on the LawExamQA_Civil benchmark using a Qwen3-8B backbone, according to the arXiv pap…
A new arXiv paper (2609.27173v1) introduces R3Con, a harness that builds context representations for large-scale reasoning using principles drawn from the cognitive theory of relevance realization, and reports it beats t…
Moggi 0.1.0-alpha, a statically typed, purely functional programming language with strict evaluation, was released today, targeting the JVM, .NET, and PHP with typed FFI for existing Java, .NET, and PHP libraries. The al…
Frigade released Yap, an open-source, on-device dictation app for macOS 26 (Tahoe) on Apple Silicon, positioned as a private alternative to Wispr Flow. Yap uses Apple's on-device Speech framework, requires no account, AP…
Wagtail released wagtail-mcp, an experimental Model Context Protocol package that exposes 50+ CMS tools to AI agents, the project announced. The server was vibe-coded with Kimi K3 and the Pi coding agent in August and in…
An MCP server exposes a data tool's capabilities to AI agents through the open Model Context Protocol, letting agents such as Claude Code, Cursor, Codex, and ChatGPT call a tool's functions directly instead of reconstruc…