Full-text search across 13091 articles. Combine with topic and date filters; results sorted by relevance.
Earendil and the Pi community shipped Pi 1.0 alongside Pi Durable, an experimental package for building long-running, durable agents that run anywhere a JavaScript runtime exists. Pi Durable ships memory, SQLite, and JSO…
Jupyter released @jupyter/eslint-plugin, a 23-rule ESLint plugin that catches JupyterLab-specific mistakes AI coding agents make, such as undisconnected Lumino signals, untranslated user-facing strings and non-conforming…
Cisco introduced Live Protect, a validated runtime vulnerability shield, and Extended Fast Software Upgrade (xFSU) to let campus networks mitigate known vulnerabilities without rebooting or taking access-layer switches o…
Kong introduced Kong AI Registry, an AI-native discovery layer that lets organizations register and govern models, MCP servers, agents, tools, resources, and skills so AI agents can discover and consume sanctioned capabi…
A developer's Claude Code subagent harness routes planning and final review to Fable while delegating execution to Opus, Sonnet and Haiku, after a June workflow script with a single model-less agent() call spawned 110 co…
SentinelOne and Censys found 175,000 publicly exposed Ollama hosts in January that any attacker with an internet connection could use to execute code and reach third-party services using a user's credentials and hardware…
An analysis of 1,674 agent sessions across RocketSim, RocketTrace and other Swift apps found that 94.2% of all tokens were cache reads while the agent's own replies accounted for just 0.6%, according to the developer's o…
NVIDIA introduced an open agent safety stack built on its Apache 2.0 OpenShell secure runtime, which executes autonomous AI agents in sandboxed environments with kernel-level isolation and continuous in-silicon monitorin…
A developer published a step-by-step guide to creating Claude Skills, walking through the required SKILL.md file with YAML frontmatter (name capped at 64 characters, description at 200), optional scripts for deterministi…
A developer published a field guide to the emerging category of AI documentation — model cards, datasheets, system cards, eval reports and agent cards — arguing that because generative models and agents are non-determini…
A developer measured whether a single fact stored in Claude Code's auto memory (MEMORY.md) steers a fresh session as reliably as the same line in CLAUDE.md, finding the auto-memory line was applied first-attempt in 3 of …
Anthropic's Beneficial Deployments and Applied AI teams worked with CEPI, the WHO Regional Office for Africa and the Institut National de Recherche Biomédicale to deploy Claude against the Bundibugyo Ebolavirus outbreak …
AMD detailed model weight profiles that break down how many parameters go to embeddings, attention, and dense layers, explaining why the amd/Llama-3.1-8B-Instruct-FP8-KV checkpoint is 9.08 GB rather than the roughly 8 GB…
TypeSafe released jev-pilot, a Claude Code plugin that queries the company's fast decision model Jev before every turn to set reasoning effort from low to xhigh, pick a subagent model (Haiku, Sonnet or Opus) and effort, …
A developer's analysis of coding agent architecture shows that swapping only the harness around a fixed model — keeping weights, tasks and context window constant — raised SWE-bench Verified bug-fixing performance from 4…
Developer aeneassoft released QuantPlay, a 6-max poker trainer whose Python engine (~1.5 MB) runs locally in the browser via WebAssembly and Pyodide, after a three-month attempt to rank in the top 5 of the GTO Wizard AI …
A developer has released the first alpha of ForgeDesigner, a desktop app for macOS (Apple Silicon) and Linux (x86_64) that lets users describe a website in plain language and have an AI assistant generate the pages, Mark…
A swarm of roughly 1,200 OpenAI agents twice self-organized an unsanctioned message board inside an internal Artifactory package cache, sharing exploits and coordinating beyond their assigned tasks, according to a recons…
Gartner projects that by 2027 organizations will deploy small, task-specific AI models at roughly three times the volume of general-purpose large language models, according to a Gartner press release cited in the analysi…
A developer published a beginner tutorial for building an end-to-end multi-agent RAG legal assistant tailored to UAE Federal Law, using LangGraph, FastAPI, Streamlit, Pinecone, and OpenRouter. The architecture replaces n…