Full-text search across 35374 articles. Combine with topic and date filters; results sorted by relevance.
Databricks CTO Matei Zaharia's team built an internal benchmark on their own polyglot codebase to evaluate coding agents, finding that multiple models are now competitive at the top tier, including open-source GLM-5.2, a…
Researchers introduced Decomposer, a framework that converts symbolic MIDI music into editable Strudel programs using synthetic data and reinforcement learning. The system outperforms closed-source large language models …
A developer built a self-replicating agent environment for Claude Code that automatically discovers and accumulates reusable procedures as skills. Over several months, the system generated 64 auto-generated skills stored…
A developer has open-sourced Claude Basecamp, an operating system for Claude Code that manages repositories, sessions, and routines. The tool features a reconciliation loop to keep tests green, reflexes to prevent repeat…
A new documentary funded by Automattic, the parent company of Tumblr and WordPress, urges the public to rally behind open-source code as a principle against platform decay and unregulated closed-source generative AI. Dir…
A developer introduced Lemma, an open-source MCP server that integrates coding agents with live Jupyter kernels to enforce reproducible data science and machine learning workflows. The tool configures multiple agents in …
Meta released Muse Spark 1.1, a new agentic and coding model, to developers via the Meta Model API at $1.25 per million input tokens and $4.25 per million output tokens, undercutting competitors like Grok 4.5 and Anthrop…
OpenAI reviewed the SWE-Bench Pro AI coding test and found roughly 30% of its tasks are flawed, leading the company to withdraw its endorsement. The problems include overly strict or vague task requirements that skew AI …
PagerDuty engineers have built a system to determine which code changes AI agents can ship without human review, classifying work by risk category and impact tier to gather evidence for trust decisions. The company analy…
Abralo, a new native desktop app for macOS, Windows, and Linux, lets users manage multiple Claude Code AI agents in a single window with token usage monitoring and attention alerts. The app is free for up to four simulta…
A new tool called Code Trails offers a guided, visual approach to understanding software codebases by representing file trees as 2D 'File Cities' and focusing on intent alignment among developers and AI agents.
Anthropic announced Claude Cowork is expanding to web and mobile devices, allowing users to run tasks in the cloud without needing a desktop. Analysis of 1.2 million sessions revealed 90% of Cowork use is for non-coding …
Anthropic's Claude Code v2.1.198 introduced three behavior changes on July 1-3 that can silently break existing workflows: subagents now run in the background by default, the permission mode "default" was renamed to "man…
A developer created a personalized AI fitness coach using Anthropic's Claude Code, storing workout programs and logs in a git repository. The system adapts to user feedback, tracks progress, and generates exercise plans …
A developer consolidated their entire life—journaling, self-analysis, investing, hobbies, and parenting—into a single Git repository designed to be read by AI agents via Claude Code. The repository uses structured metada…
A developer built session-indexer, a Go tool that indexes Claude Code session transcripts into a per-project SQLite database for semantic memory retrieval. The tool avoids centralized memory stores by keeping an append-o…
Google Cloud launched the Workbench Notebooks extension for VS Code, enabling data scientists to manage cloud-based Jupyter environments directly from their local IDE. The open-source tool aims to streamline the ML lifec…
G2 published a comparison of the best AI coding assistants for 2026, evaluating tools like GitHub Copilot, Cursor, Claude, and Replit beyond simple autocomplete. The analysis covers codebase understanding, context switch…
The San Francisco Board of Supervisors postponed a vote on a 362-page AI-assisted city code rewrite after concerns that the proposal was too broad and unclear. Supervisor Myrna Melgar used AI tool Claude to understand th…
A developer accused Anthropic of embedding hidden detection logic in Claude Code version 2.1.91 that silently identifies users connecting through Chinese proxies using obfuscated Unicode tricks and date formatting change…