Full-text search across 68259 articles. Combine with topic and date filters; results sorted by relevance.
The author retired their 90s-era guestbook, which was built with nearly 30-year-old Perl code from Matt's Script Archive, due to an increasing inability to filter out hate speech and spam without using modern, non-period…
Taskhold measured the context-window cost of its own MCP server at roughly 8,000 tokens across 22 tools, and cut it to about 7,200 by replacing the 180-character regex that zod's .uuid() writes into all 20 id fields with…
A paper titled "Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand" reports that its BestRand method cuts high-error risk by 50.2% and estimation error by 16.4% versus competing benchmark-com…
Dropbox engineers Daniel Reiter Horn and Rich Chan turned two separate side projects into the agent now powering task execution in the new Dropbox experience, which lets users ask questions about their content and reques…
A developer building Refmade, a desktop app that visualizes Claude Code and Codex sessions as an office, disclosed that the project ran for 17 days without version control until an agent created a private repository on O…
At a Quito Lambda session on October 28, Stack Builders developer Gandhy García demonstrated an AI coding agent debugging a Python/FastAPI DynamoDB game API against a locally emulated AWS environment via LocalStack, usin…
Isoform released an open-source Mac app that observes a user's activity on the computer, stores memory on disk, and routes model work to the user's own Claude Code, Codex, or Ollama rather than shipping its own model. Th…
Fyslide launched as a local-first desktop app for Mac (with a Windows beta) that uses a user-supplied AI model to generate up to ten TikTok slideshows or Instagram carousels from a single topic, with all files stored in …
GitHub released verified MCP connectors for Copilot, offering 26 pre-configured, GitHub-vetted services that require a single sign-in and persist across the Copilot app, CLI, VS Code, cloud sessions, and GitHub Mobile. T…
Vercel's AI Gateway now serves Moonshot AI's Kimi K3.1 Pro and Kimi K3.1 Pro Highspeed through additional Zero Data Retention (ZDR) providers, where Moonshot AI had been the only provider for both models. Both models off…
MV2 of Munim, Inc. coded 44 federal protective orders governing AI use in discovery and tested six pre-registered predictions about whether they permit running open-weight models on a firm-controlled server. Three predic…
QuickProof, a tool that lets developers write formal specifications for C code as small C programs, turns those specs into Rocq theorems that AI agents then prove, with the Rocq proof checker verifying every step so noth…
A new open agent skill called scan-to-vector, published with a SKILL.md file for Claude Code, Codex and other compatible clients, rebuilds scanned pages as searchable vector PDFs rather than OCR text overlays, and its au…
JetBrains open-sourced ThinkRail, an agentic IDE that runs each AI agent session in its own git worktree, under Apache 2.0 for macOS, Windows, and Linux. ThinkRail is built on Earendil Works' MIT-licensed Pi coding agent…
Anthropic built a custom source control system called Scion after its daily merged code changes rose from about 2,500 in May 2026 to over 30,000 by September 2026, straining Git and its roughly 25 million daily CI checko…
OpenAI said in a post on X that ChatGPT and Codex now help engineers design and test hardware, citing a large semiconductor client that saw roughly 48% time savings in directed test generation, a chip verification step t…
The Allen Institute for AI (AI2) released StateBench, a long-context state-tracking benchmark with four difficulty levels — R-trivial, aperiodic, soluble and general finite — that test whether language models can follow …
PagerDuty announced Paige, an SRE agent that joins on-call rotations and works incidents alongside engineers, handling diagnostics, coordinating responders in Slack and Zoom, and drafting post-incident reviews, with guar…
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…
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…