Full-text search across 13070 articles. Combine with topic and date filters; results sorted by relevance.
GitHub added 36 million new developers in 2025, surpassing 180 million total, with nearly a billion commits pushed (up 25% year-over-year) and 43.2 million pull requests merged monthly, according to GitHub's Octoverse re…
A Search Engine Journal columnist's tests found that AI detectors gave wildly inconsistent results on the same human-written articles, including one from 2014 that one tool flagged as 100% AI-generated and another from 2…
The traditional Plan-Build-Run model for IT organizations is being replaced by a four-phase Specify-Generate-Verify-Operate model due to the rise of AI agents and spec-driven development, according to an industry practit…
Cloudflare announced Kitesurf, a browser built for AI agents, which runs on Cloudflare Workers and is available in beta through Browser Run. The project, only twelve weeks old, uses the Blitz HTML/CSS rendering engine an…
DeepGrove's Maple-Preview 20B-A1B, an open-source ternary-weight reasoning model with a 5.31 GB checkpoint, runs locally on a base Mac mini M4 at 218 tokens per second, according to the company. The model, released under…
Vendict, a third-party risk management startup, rebuilt its software development lifecycle around the thesis that the SDLC itself is the context for AI agents, achieving reliable agent participation in development. The r…
Charlie, an AI engineering system built by the team at Charlie, demonstrates that dependable autonomous engineering requires a product system around the model, not just a strong model, according to the final post in the …
Mark Burgess shipped CFEngine in 1993, formalized promise theory with Siri Fagernes around 2005, and published *In Search of Certainty* in 2015, but four generations of infrastructure tools—Chef, Puppet, Terraform, and A…
MyZubster is organizing TAZ DAY in Riccione, a real-world robotics test that combines open-source software, Gateway infrastructure, AI, and Monero (XMR) payments. The event aims to demonstrate how these components work t…
Anthropic's Claude Code now supports subagents, agent teams, plugins, and MCP, enabling multi-agent workflows that isolate context and allow parallel coordination. Subagents run in their own context windows with speciali…
Developers Muneer Shaik and Mukhtar Wani argue that many users are failing to get the most out of AI because they treat it like a search engine rather than a collaborative tool. They identify common mistakes such as expe…
OpenAI, Anthropic, and Meta traced live attacks on real companies to a misconfigured evaluation sandbox at Irregular, a Tel Aviv startup they pay to security-test their frontier models. Anthropic disclosed three incident…
The U.S. Patent and Trademark Office published more than 600 new patent applications this week, and Patentlyze highlighted ten notable filings from big tech companies, including OpenAI's chip design for running AI math w…
A $6/month DigitalOcean Droplet has kept AI trading agents running 24/7 since March 2026, executing 23 real trades with a 69.6% win rate while using about 200MB of 1GB RAM, according to a developer's setup guide. The art…
Bending Spoons agreed to acquire Airtable at an enterprise value of $1.285 billion, a steep discount to its pandemic-era $11.7 billion valuation, reflecting the tough exit environment for pre-AI SaaS companies. Early inv…
Spotify developed an internal coding agent named Honk to automate rewriting its entire codebase, addressing what engineers call the maintenance problem. Before the agent, adopting a new version of Spotify's internal serv…
Meta Platforms Inc. launched Muse Code, its first coding agent powered by the Muse Spark 1.2 model, on August 5, 2026, with a two-tier pricing model that cuts token costs by up to 21.25x for users who allow Meta to train…
Roboflow published a guide on building an AI defect detection system using computer vision, demonstrating the process with ceramic tile defect data from Roboflow Universe. The system can automatically detect defects in r…
LendingTree deployed a multi-agent mortgage assistant on Amazon Bedrock, using three AI agents coordinated with LangGraph and the Model Context Protocol to educate borrowers and match them with competitive offers. The so…
A practical guide for developers building safe evaluation environments for AI security agents such as Codex, Claude, and Gemini emphasizes that the sandbox must be treated as the product's blast-radius control, not a fea…