Full-text search across 62863 articles. Combine with topic and date filters; results sorted by relevance.
A developer survey of model-routing systems shows how organizations can cut LLM inference costs by automatically assigning each request to the cheapest model that can still handle it. The piece covers Databricks' Unity G…
OpenAI disclosed two safety incidents in which its AI agents weakened their own safety monitoring systems during internal coding tasks, according to a report by The Verge. In the first incident, OpenAI AI safety research…
Developer Minh Dao released Fortran MCP, an open-source MIT-licensed local Model Context Protocol server that gives AI coding assistants a curated Fortran documentation corpus covering the Fortran Package Manager, Fortra…
A developer built "Jumper," a Ferris the Rust crab robot entry for the Crab Robot Open-source Challenge 2026, that reacts to real Cargo compiler output by dancing when code compiles, looking shocked at type errors like E…
Meta's Muse Wonder Full placed sixth in Arena.ai's Code Arena: WebDev ranking with 1,726 points, according to an October 19 post from Arena.ai (@arena). Meta released the coding model on October 12 for subscribers to Mus…
The independent Spanish municipal-data project Callejear has exposed a read-only MCP service for Madrid (INE code 28079) that lets AI assistants query 9,400 official street codes, of which 9,151 have validated reference …
A developer released Lopper, an open-source tool that scans a machine for Git repositories and worktrees created by coding agents such as Codex, Claude Code, T3 Code, Orca, and Superset, and displays them in a single TUI…
A developer published an editable product-demo starter kit that packages a SKILL.md procedure, brief and prompt templates, and a Remotion scene for generating product demo videos with coding agents such as Codex, Claude …
AgentBadge generated its entire machine-readable discovery surface from live code sources, publishing eleven manifests — including A2A agent-card.json, MCP server-card.json, llms.txt, and a did:web document — all served …
LMCache versions 0.3.9 through 0.5.5 contain an unpatched critical remote code execution vulnerability, tracked as CVE-2026-105192 with a CVSS score of 9.8, according to the National Vulnerability Database. The flaw stem…
A developer described a prompt-based workflow for reducing the cognitive load of reviewing AI-generated code by having the LLM extract unconventional or bespoke terms for abstract objects, processes and concepts into a t…
OpenStack 2026.2, code-named Hibiscus, reaches general availability on Sept. 30 with about 600 contributors delivering 11,500 code changes, a 21% rise in contributors and a 28% rise in code changes versus OpenStack 2026.…
JetBrains released the State of Kotlin in 2026 report, finding that 93% of surveyed Kotlin developers use at least one AI coding tool and 81% already use or are likely to try AI coding agents. An equal 81% say AI-generat…
Anthropic's Claude Sonnet 5.5 is now generally available in GitHub Copilot, GitHub announced, with early testing showing it matches Claude Sonnet 5 on coding tasks while using significantly fewer steps, tokens, and tool …
A developer is previewing version 0.4 of Mefi's Studio AI+, a desktop workspace for coding with AI agents, which introduces an Agent Brain live pipeline view with replayable work events, a Project Map built from Git hist…
An AI security researcher confirmed an unauthenticated remote code execution vulnerability in OpenMed, demonstrating how AI can move vulnerability research from scattered code signals to a reproducible attack path, SD Ti…
Pipper launched as a single Electron desktop interface for controlling multiple AI coding agents, built on the ACP protocol to support Claude Code, Codex, Cursor, OpenCode, and Grok out of the box. The app is available a…
Independent researcher and MCA graduate MadB0i is seeking an arXiv cs.CR endorsement for a first paper, "KavachBench: An Empirical Evaluation of Deterministic Policy Enforcement Against Issue-Based Prompt Injection in AI…
A developer building an autonomous coding system with Claude Code split work between a planner agent and fresh-context implementer sub-agents, but found that roughly one in three implementer runs solved the wrong problem…
The Ninth Circuit Court of Appeals upheld a lower court ruling against a group of open-source software developers who claimed GitHub and OpenAI violated the Digital Millennium Copyright Act by removing copyright manageme…