Full-text search across 69207 articles. Combine with topic and date filters; results sorted by relevance.
Meta introduced the Muse Wonder and Muse Wonder Full models, which the company says deliver state-of-the-art performance on personal and professional agentic tasks, built on the groundwork of Muse Spark. The models add A…
AWS published a guide for deploying decision models with llama.cpp on Amazon SageMaker AI, using the AWS Deep Learning Container for llama.cpp to serve OpenAI-compatible chat completions through InvokeEndpoint. The post …
PonyMux 0.13 added an Inspector that collects the pull requests, links, and outputs an AI coding agent produces during a running conversation, listing them newest-first with real page titles pulled from the pages themsel…
Researchers submitted RATED (Reliability-Aware Tool Retrieval via Execution Dynamics) to arXiv on 9 Oct 2026, a retrieval framework that pairs a frozen dual-encoder with contrastive fine-tuning for semantic matching and …
Researchers submitted Oído, an inference engine that runs open-vocabulary English speech recognition entirely on a $5 ESP32-S3 microcontroller with no neural accelerator, executing a 13M-parameter Conformer-CTC model wit…
Cline ranked #1 among 100 evaluated agents with a score of 87.8 in the week of 2026-10-12, according to the weekly agent rankings. Deepseek-harness posted the largest drop, falling from rank 16 to rank 100 (-84), while n…
Apple introduced a JSON-based project configuration format for Xcode 27.2, replacing the property-list-based project.pbxproj file with project.xcproj to reduce merge conflicts and make project settings easier for AI codi…
A developer built Doorstep, an open-source accessibility-focused walking app that takes a user's daily physical distance limit as input, filters nearby OpenStreetMap places in code to those within that ceiling, and uses …
A developer built UNSEEN, a walking game that uses a local open-weight vision model (Qwen3-VL-2B-Instruct via Ollama) only to describe photos as structured data, while deterministic code — an "evidence gate" — decides wh…
A developer built Sproutpatch, a local-first daily check-in web app that pairs a user-installed Gemma model with plain TypeScript rules to nudge people outside. The Gemma model (gemma3:1b via Ollama, or Gemma 3 270M on-d…
Meta's Muse Wonder model is now available on Vercel's AI Gateway under the model name meta/muse-wonder-1.0, giving developers access without a separate Meta account. The model targets coding, long-running agents, and com…
CrowdStrike Intelligence disclosed that a financially motivated, suspected Chinese-speaking threat actor used ARTEX, an open-source agentic penetration testing tool developed in China by Autumn-27, to breach South Korean…
ArtCraft's Brandon Thomas is using Claude to build open-source Rust recreations of Adobe and Microsoft Office applications, including PhotoCraft, WordCraft, GridCraft and DeckCraft, with PhotoCraft's 11 October roadmap r…
A developer outlines a changelog habit for managing Anthropic model identifiers, arguing that hardcoded model strings scattered across application code, Terraform variables, CI secrets and dashboards create avoidable out…
A developer built Crew, an open-source plugin for Hermes Agent that replaces an AI coding agent's self-reported "done" status with a frozen verification command that must exit 0 before a task card can close. The system a…
A developer built a Kaggle Benchmarking Challenge submission that tests AI models on a single resilience question: whether an HTTP request should be retried after a failure. The benchmark probes whether models understand…
A developer built Touch Grass Planner, a local-first web app that uses a locally running Gemma 3 4B model via Ollama to write short outdoor outing plans, then dims the screen to a dark countdown timer with a route map. T…
A developer released `dirigista`, an MCP server that exposes three classification tools — `verify`, `categorize` and `score` — to MCP clients including Claude Code, Claude Desktop and Cursor, returning typed judgments wi…
A developer built Browser Cookie Bridge, a macOS app that transfers cookies from Chromium browsers like Brave into AI coding agents' in-app browsers so agents can start from existing logged-in sessions. After hitting RAM…
A developer comparison of ElevenLabs and Google Cloud Text-to-Speech finds ElevenLabs delivers higher-fidelity, more expressive neural voice output with instant voice cloning from as little as 10 seconds of audio, while …