Full-text search across 3473 articles. Combine with topic and date filters; results sorted by relevance.
Researchers introduced KCoral, a lightweight benchmark server that decouples GPU execution from AI agent loops so many agents can share a small pool of GPUs. KCoral uses an atomic HTTP protocol with four operations — upl…
A developer's guide explains that the Model Context Protocol (MCP) standardizes how AI applications discover and call external tools, resources, and prompts, but does not by itself make an agent secure. It walks through …
Wren AI released four working embedded analytics demos for capital markets, retail, healthcare, and insurance that place a governed Wren AI conversational thread inside a host product, with the host signing a JWT carryin…
T version 0.55.5 "L'Ultime combat" has been released, offering a hermetic dependency graph that orchestrates Julia, Python, and R pipelines through Nix and passes DataFrames between nodes via Apache Arrow IPC. The tool, …
Two open-source projects, Kev and Laya, emerged within days of TypeSafe's closed-weight Jev launch, with Laya surpassing 19,000 GitHub stars and Kev matching Jev within a point on new sources (0.851 vs 0.857) while trail…
LeRobot's dataset visualization tool lerobot-dataset-viz inspects recorded episodes — camera frames, robot state and action streams, and episode timing — but does not track training loss, according to a community breakdo…
Anthropic's Claude Opus 5.5 and Claude Sonnet 5.5 are now available on Amazon Bedrock in AWS GovCloud (US) Regions, giving organizations with regulatory and compliance requirements, including ITAR, an on-ramp for AI-assi…
A developer rebuilt a five-agent research pipeline after discovering that accuracy degraded as accumulated context grew, a phenomenon Chroma's 2025 research terms "context rot" — testing 18 frontier models including GPT-…
A developer walkthrough shows how to connect Anthropic's Playwright MCP server to Claude Code so the agent reads locators from a live browser's accessibility tree instead of guessing selectors from source code. The setup…
ZQK (Zen Quantum Kernel) launched as an open-core, distributed Cellular Knowledge Operating System written in Go, installable via Homebrew with `brew tap zqk-os/tap` and `brew install zqk`, with pre-compiled release arch…
A developer published a guide for building a privacy-first local AI coding assistant using open-weight models such as Meta's Llama 3 8B and Mistral 7B served through the Ollama runtime, keeping proprietary code and data …
A growing body of 2026 research shows that an AI agent's harness — its loop, context management, tool interface and recovery logic — drives benchmark performance far more than the underlying model weights. Harness-Bench …
A solo hackathon entrant built Third Umpire, a single-container Django and SQLite judging portal that models each review as event average plus project quality plus judge leniency plus noise, fitting quality and leniency …
Tencent Zhuque Lab contributed RogueHandoff-20, a 20-scenario benchmark added via GitHub PR to Tencent's AI-Infra-Guard project, which shows that injecting unsafe intent into the transition between agents raises harmful-…
KingKong Robotics released Jumper, an open-source 22-DoF crab robot project whose repository is designed to be opened in an AI coding assistant so users can describe desired appearances, motions and scenes in one sentenc…
DeepSeek and Huawei Technologies unveiled a suite of open-source programming tools for Huawei's Ascend AI chips on September 30, 2026, centered on TileLang, a high-level language pitched as a simpler alternative to Nvidi…
A maker built a voice-activated HAL 9000 assistant using a Raspberry Pi Zero 2 W, a ReSpeaker 2-Mics Pi Hat, and a Moebius Models 1:1 scale HAL 9000 model kit, with all speech processing self-hosted on a homelab server r…
Google Research published TurboQuant on March 24, 2026, a KV-cache compression algorithm that shrinks long-context memory to 3 bits per value with no accuracy loss, cutting a 16GB cache for Llama-3.1-8B at 128K context t…
A developer comparison of OpenAI Codex and Anthropic's Claude Code finds both tools priced at $20 and $200 per month but built differently: Codex bundles into ChatGPT with GPT-5 and o3 models, while Claude Code is a term…
Andrej Karpathy proposed an "LLM Wiki" pattern on April 3, 2026 that replaces retrieval-augmented generation with a persistent, LLM-maintained markdown knowledge base, where raw source documents are compiled once into in…