Full-text search across 71140 articles. Combine with topic and date filters; results sorted by relevance.
SlopCodeBench's October 2026 run found gpt-6 Astra posting the highest strict pass rate at 16.3%, up from gpt-5.5's 14.8% in May, across 36 problems and 196 checkpoints per setting. Author Dex Horthy reported that medium…
Anomaly released OpenCode 2.0 on 12 Oct, a "major overhaul" that runs the OpenCode server as a single background process shared by its terminal, web and desktop apps, opts MCP servers into codemode by default, and ships …
A Sonatype Nexus user reported that upgrading the container from sonatype/nexus3:3.76.0-java17-ubi to the latest version broke RPM build pipelines with sha256 checksum mismatch errors and also moved the installation from…
Obelisk released version 0.42, splitting its single server.toml policy file into three files with three owners — server.toml for the platform, app.toml for the app policy, and deployment.toml for the application — so tha…
LLVM 23.1.0 was released on August 26, 2026, with almost 1300 patches contributed by Arm teams across architecture support, libraries, tools, performance and ML workloads. The release adds support for the Arm AGI CPU, Ar…
NVIDIA released DOCA AI agent skills on GitHub, a set of SKILL.md-based specifications that give AI agents verified API signatures, hardware capability requirements, and build constraints for developing on NVIDIA BlueFie…
An AI safety team developed and deployed a basic live per-action monitor that uses an LLM judge to review each agent action before execution and halt evaluations for human review when an action exceeds a harm threshold, …
A security researcher tested 24 exfiltration payloads against a deny-by-default Tensorlake Sandbox configured with a single allowlisted destination, api.github.com, and none of the payloads delivered a token to the attac…
A developer has published a tutorial on building a web application that uses OpenAI's Images API to turn drawings into photorealistic images. The app is built with Python and Anvil, and the tutorial walks through creatin…
GitHub Copilot, Claude, LangChain, and Spring AI all support custom AI skills under different names—Extensions, Tools, MCP servers, and Functions—but share the same core architecture of schema, implementation, and regist…
A developer published an experimental guide for running long-lived AI agent loops on a cost-optimized Hetzner Cloud ARM VM (CAX33), using zellij to keep the OpenCode server and ngrok tunnel alive and driving the agents f…
Opsera's study of 937 Forge projects found that rework per task fell from 3.2 tries to 1.3, delivery time dropped 70-85% against a 10-hour/story-point baseline, and token spend per work order fell roughly 75%, attributin…
OpenAI is ending its native integration with Cursor, citing concerns that SpaceX, which acquired Cursor, could misuse its models given a history of terms-of-service violations, including a distillation dispute involving …
MacOS MLX Control Center v0.4, a 1-click web GUI and CLI tool for running local multimodal vision and text LLMs on Apple Silicon M-Series processors, has been released. The update adds full native integration with mlx-vl…
Uber reported that more than 70% of its pull requests are now attributed to local or cloud agents, with over 3,600 agent skills built and more than 30,000 agent skill executions per day. From February to August 2026, wee…
Anthropic's most expensive model, Fable 5, has seen spending plateau at about 11% of total spend on the company's tools more than two months after launch, while its smaller Opus 5 has already surpassed Fable in business …
A 2026 survey of AI-powered privacy policy generators found that tools like PrivacyGPT and PolicyCraft are now production-grade, with PrivacyGPT fine-tuned on 10 million privacy statements and PolicyCraft achieving confi…
A developer found that an AI-generated file upload endpoint passed all functional tests but contained a path traversal vulnerability, allowing attackers to write files anywhere on the server. The developer recommends a 1…
Moonshot AI released the weights for its Kimi K3 model with 2.8 trillion parameters and a 1M token context window under a new Kimi K3 License, which allows inference providers like Modal, Baseten, Fireworks, DigitalOcean…
Air Pipe has published a guide demonstrating how to build a production-ready MCP server using a Postgres database, a single config file, and a token, with a setup time of about 15 minutes. The tutorial covers creating a …