Full-text search across 70885 articles. Combine with topic and date filters; results sorted by relevance.
Io.github.smigolsmigol/llmkit v0.4.10, an AI cost tracking tool for spend, budgets, and Claude Code, Cursor, and Cline costs, was published to the official MCP registry on 2026-08-27 and is distributed as @f3d1/llmkit-mc…
A developer has released Pannonico, a static site generator written in Go that integrates Vite and supports HTML or Markdown, layouts, partials, and structured data. The tool includes an MCP server for AI-assisted develo…
SandboxAQ announced Switch, open-source software that integrates AI agents into team collaboration tools such as Slack, Microsoft Teams, and Discord, available at no cost and deployable in minutes. The platform is model-…
OpenMuster has launched a real-time observability layer for AI agents, providing developers with a live task stream that shows what agents started, finished, and when human input is needed. The tool integrates with MCP a…
A developer building a cloud AI coding agent read every message sent by its first six users and found that the worst bug was in the agent's own progress reporting. The agent's fallback summary only counted file writes an…
Reuters reports that Meta Platforms Inc. explored slashing some teams by as much as 60% under a plan code-named Project OT to shift work to AI agents, but employee revolt and disappointing productivity gains led CEO Mark…
A new approach to safely allow AI coding agents to run `git push` from sandboxed VMs uses a short-lived GitHub token injected by a proxy outside the sandbox, avoiding exposure of real credentials. The method, detailed in…
Side, formerly PTW, has signed a six-month memorandum of understanding with Danish AI firm Modl.ai to develop an AI-enabled quality assurance system for games. The system, which requires no access to source code, uses AI…
An independent researcher is seeking an arXiv endorsement for a paper titled “Diagnosing the Measurement Problem in AI Evaluation: Four Structural Failure Modes Across Six Benchmarks,” which analyzes six AI evaluation be…
Neurosurgeons at the National Hospital for Neurology and Neurosurgery (NHNN), part of University College London hospitals NHS foundation trust, performed the world's first successful AI-assisted operation to remove a bra…
Tencent's WeChat Vision team has open-sourced WeMM-Embedding, a family of multimodal embedding models for representing and matching text, images, videos and other content types, with 2B, 4B and 9B versions. The 9B model …
In an interview with Help Net Security, Rob Janssens, EMEA Cyber Security Director at Hikvision Europe, said AI will not fix governance problems in camera estates, emphasizing that products should let customers recover c…
Nutanix CEO Rajiv Ramaswami said the company spent $20 million on its own on-premises AI cluster to reduce reliance on external AI coding tools like GitHub Copilot and Anthropic's Claude, and expects to recoup the invest…
Researchers released HealthBench-Psych and HealthBench-Psych-Hard, a mental-health subset of OpenAI's HealthBench, comprising 610 clinician-validated conversations (12.2% of the original 5,000-physician-rubric corpus). E…
Researchers introduced a lightweight multimodal vision-language framework adapting TinyCLIP for early-stage apple fruitlet classification, achieving F1-scores of 0.95 for calyx, 0.98 for fruitlet, and 0.85 for peduncle o…
Researchers introduced ClueWeaver, a reward-guided dual-agent framework that improves question answering on long literary narratives using compact local language models. The framework, detailed in arXiv:2608.25531v1, use…
Researchers propose Prefix Sliding, a method that discards intermediate reasoning tokens during test-time scaling, capping memory use and enabling existing models to run 3x faster without training while maintaining perfo…
Researchers released MTDiag, a multi-turn diagnostic dialogue dataset built from DDXPlus, MIMIC-IV, and published case reports, to evaluate large language models (LLMs) as diagnostic agents in dynamic clinical encounters…
Andy Hamilton released Critter, a keyboard-driven TUI for reviewing GitHub pull requests and coding agent changes, installable via `cargo install --git https://github.com/andyhmltn/reviewer`. The tool integrates with Git…
Fwozen v1.0.0, a tool that freezes and unfreezes merges across a GitHub organization with an audit trail, was published to the official MCP registry on 2026-08-27. It is distributed as a hosted remote over streamable-htt…