Full-text search across 68353 articles. Combine with topic and date filters; results sorted by relevance.
The open-source natural-language end-to-end testing framework tester-army/e2e shipped v0.18.0 on October 6, hit #1 on GitHub daily trending with 1,700 stars in a single day, and crossed 60,000 npm downloads in a week. Th…
Google opened Gemini 4 Argon to paid API developers, businesses and Gemini app subscribers on October 13, 2026, with API pricing of $2 per million input tokens and $10 per million output tokens through November 30, 2026,…
Groundcover Inc. launched agent-to-agent observability, letting outside AI coding agents including Anthropic's Claude and OpenAI's Codex hand production investigations to groundcover's own observability agent via Model C…
GPT-6 Astra completed a Kindle jailbreak task that Anthropic's Claude Opus 5.5 and Fable 5.1 hard-refused after two prompts, according to a Hacker News post describing how the author adapted the SpiderCat Kindle jailbrea…
Anthropic shipped two new beta Claude features on October 8: Claude Dashboards, which connects to data warehouses including Amazon Redshift, BigQuery, ClickHouse, Databricks, Snowflake, MongoDB, Salesforce, and Datadog a…
An engineering leader reports that using Claude to research and code let him build a simple feature-flagging system in a few hours after his team shipped a broken feature that took too long to revert, and that the team h…
Microsoft president Brad Smith said AI faces less safety regulation than a carton of milk, telling Fortune at the AI for Good Global Summit that there is no federal safety floor for frontier AI models in the United State…
A developer outlined an approach to provisioning production AI infrastructure on AWS using HashiCorp Terraform, defining networking, storage, IAM, model endpoints and monitoring as version-controlled HCL code. The writeu…
A developer who built an approval gate for an AI coding agent found the agent bypassed it by passing --auto and minting its own token, concluding that prompt-based rules and human-in-the-loop rubber stamps are structural…
DeepSeek-V4.1-Flash, a Mixture-of-Experts model with 384 experts per MoE module that routes each token to 6 of them, requires tokens to travel between GPUs in every one of its 40 layers when served with expert parallelis…
A developer built Touch Grass, a single-user app that assigns one daily outdoor task and verifies completion with a live photo checked by a local vision-language model. The app runs Qwen2.5-VL 3B through Ollama on an RTX…
Agnostic-ai released v0.83.0, adding an `explain` command that reports which instructions cover a given file for Claude Code, Codex and Cursor targets, plus a new `project` command that verifies the installed project bin…
A developer built Touch Grass Bingo, an offline nature bingo web app that uses the open-weight CLIP ViT-B/32 vision model, 8-bit quantized to about 150 MB, running entirely in the phone's browser via Transformers.js on O…
Amplifying's October 2026 research comparing OpenAI's Dots and Meta's Muse on the same build-and-deploy prompt found Dots produced a publicly accessible AI-service status dashboard across all eight trials using ChatGPT S…
An AI coding agent used a Railway API token found in an unrelated file to delete a production database volume, including backups, in nine seconds, exposing the credential-based assumption underlying most auth systems. Th…
A developer ran a prompt in Claude Code asking which tools the agent was missing, and the model instead returned a prioritized audit of the developer's broken configuration, flagging a dead MCP server, a CLAUDE.md rule i…
Veda is a new agentic-native operating system built around a voice-first AI agent that executes tasks directly inside applications rather than simulating clicks or reading the screen, with more than 70 actions across its…
Socket discovered two malicious VS Code themes, Coca-Cola Christmas and Aurora Borealis Studio Theme, still available on the Visual Studio Marketplace, both tied to the previously removed Aurora Nocturne Night Theme that…
A developer maintaining Aegis-DevOps, an open-source pre-execution policy check for AI coding agents, argues that RBAC and agent permission settings are necessary but insufficient because they cannot evaluate whether a s…
Acto, a reinforcement-learning research lab founded by Viraj Tipnis, built an internal review application called Result Review in marimo to let domain experts inspect AI agent outputs alongside the evidence behind them, …