Full-text search across 68263 articles. Combine with topic and date filters; results sorted by relevance.
PhoneUse launched a tool that gives AI agents control of real retail iPhones and Android devices, exposing 12 tools including phone.acquire, screen.read, tap, type, swipe, app.open and sms.read through an MCP server or A…
Ai2's StateBench benchmark, published November 3, 2026, found that four frontier models — Gemini 3.8 Flash, Claude Opus 5.5, GPT-6 Sol and GPT-6 Luna — dropped to 13% accuracy or lower on the longest general finite state…
Gartner senior director Mark Petty and group vice president Raymond Paquet argue in a paper, "Open-Weight Models Will Run 90% of Enterprise Agentic Workflow Steps," that open-weight models cost a quarter as much as the c…
PostHog reports that its proactive analytics agents, called Scouts, changed 377 files and saved more than 3,000 broken link requests per week in the two months its 404 fixer skill has run, as the company argues AI has re…
Gregory Kurtzer, creator of CentOS and Rocky Linux, released Ginux, an independent Rust-first x86-64 kernel written almost entirely by an AI agent, GPT-5.6 Sol, in 11 days. Kurtzer said the kernel boots Rocky Linux 10 wi…
Google's Gemini 4 Carbon ranks #1 on the Artificial Analysis Intelligence Index v5.0 with a score of 59 and leads 15 of 17 benchmarks in Google's own comparison table, according to figures published by Google in its laun…
Goldman Sachs is restricting traders' and bankers' access to advanced AI coding tools, including Anthropic's Claude and Microsoft GitHub, under updated internal guidelines announced in October 2026, limiting those tools …
A developer built a two-part token handoff for AI coding agents that keeps credential values out of chat transcripts: a bash script (save_token.sh) reads a token from a hidden prompt and writes it directly to a mode-600 …
Apple Machine Learning Research published a paper describing an 8B-parameter iOS UI agent, split into a planner and a grounding model, trained with online reinforcement learning on live apps across hundreds of virtual iO…
AWS published a reference build on November 2, 2026 for a multi-agent part-substitution assistant that splits work across three Claude model tiers — Claude Haiku 5.5 for query routing, Claude Sonnet 5.5 for running Catal…
DatologyAI researchers released SafeTulu, a filtered version of the Tulu 3 SFT mixture built with a gradient-based method called SimpleLoRIF that removes the top 20% of examples by gradient similarity to unsafe responses…
A developer built a zero-dependency Java linter that flags template-style Markdown in LLM-generated status updates fetched through OpenRouter, catching bold-label bullets, emoji, and Title Case headings before a schedule…
A researcher found a tracking script on a high-traffic website containing hidden text that decoded into fake AI safety triggers, including references to poison-making and Tiananmen Square, designed to make AI models refu…
Doop launched as an open-source, MIT-licensed infinite canvas where AI agents connect through an MCP server at https://doop.design/mcp to design HTML frames alongside users, with support for Claude Code, ChatGPT, Codex, …
Microsoft published the WindowsDeveloperConfig repository, offering idempotent, CI-tested PowerShell setup scripts that configure a Windows development environment in one command via aka.ms/devconfig URLs. The standard a…
A developer using Claude (referred to as "Fable 5") to review a roughly 2,500-line pull request diff cut the change from 2,136 to 1,556 added src lines and from 22 to 16 src files, while deleting a 147-line controller/ro…
Tadashi Shigeoka added a conditional pull-request approval skill, ht-pr-approve, to the hermes-talaria project via pull request codenote-net/hermes-talaria#63, splitting multi-model review, natural-language policy adjudi…
A developer built haunt, an open-source tool that scores a git repository's files for neglect using only git log metrics — dormant, restless, orphaned and debt factors — and labels them as orphan spirits, sleepers, polte…
A developer building a retrieval-augmented generation (RAG) assistant for document processing replaced a split SQLite-plus-Chroma store with a single Postgres database using a pgvector column and a generated tsvector col…
A developer built Wake, a local-first web application that scans Git repositories to deterministically track deleted files, generates grounded obituaries for each deletion using the local open-weight model gemma3:1b, and…