Full-text search across 31918 articles. Combine with topic and date filters; results sorted by relevance.
Harness Score, an open-source scanner that measures how well a code repository is set up for AI coding agents, has released version 1.5 with customizable scoring, multilingual documentation, and a GitHub Marketplace Acti…
A 14-year analysis of a source-code sharing platform shows new registrations plummeting from 87,000 in 2018 to 2,000 in 2025, with cash top-ups falling from 8.3k to 130 users, as AI tools commoditize low-value code snipp…
Anthropic's Claude Opus 5 is closing the gap with Mythos-class model Fable 5 on complex coding tasks, according to developer benchmarks. In tests on asynchronous race conditions in TypeScript, Opus 5 correctly implemente…
A developer released a free multi-agent routing setup for Claude Code that dispatches a single prompt to specialist subagents—research, build, write—running in parallel and merges the results. The drop-in configuration u…
Sakana AI announced Fugu-Ultra v1.1, an upgraded orchestration engine that delivers performance gains of up to 7.9 points over v1.0 and beats leading models like Fable 5 in complex coding and reasoning tasks, available a…
Forkbench v1.4.63, a native-Mac control room for running CLI coding agents, is now available as a free .dmg for macOS 14+. The app lets users manage a team of AI coding agents on one board, with local-first secret storag…
Anthropic's Claude Code product team, led by Cat Wu, advocates for a 'lean harness' approach to AI coding tools, avoiding opinionated features that pre-structure codebase context, as rapid model improvements make long-te…
Princeton and Stanford researchers released mini-swe-agent, a coding agent in roughly 100 lines of Python that scores over 74% on SWE-bench Verified, beating Claude Code's scaffolding by six percentage points when using …
A developer built tastemaker, an open-source skill for Claude Code, Cursor, Windsurf, and Codex that locks a design system before AI writes any UI code, preventing the generic indigo-gradient look common in AI-generated …
MacOS ships with a built-in command-line tool called caffeinate that prevents the Mac from sleeping, making it especially useful for keeping Claude Code and Codex sessions alive during long-running terminal tasks over of…
Google has delayed the release of Gemini 3.5 Pro, originally expected in June, due to disappointing coding performance after a late-June training data reset, according to Bloomberg. The company said it is currently testi…
A threat actor breached AI music generator Suno by compromising a single employee with the Shai-Hulud worm, then used harvested GitHub and cloud credentials to access the company's source code, customer list, and Stripe …
Fuse, a free open-source .NET tool, speeds up Claude Code on C# codebases by indexing solutions through MSBuild and Roslyn into a persistent semantic graph stored in `.fuse/fuse.db`, reducing token usage by 38 to 44 perc…
Dimitris launched OtoDock, a self-hosted platform that runs Claude Code and Codex as a team of agents on a server, with a live dashboard, MCP framework, and multitenant support for businesses. The Fair Source license all…
Chamath Palihapitiya is returning to a day-to-day operating role as CEO of 8090 Labs, the AI coding company he founded in January 2024, after raising a $135 million Series A led by Salesforce Ventures. The company's prod…
On July 8, 2026, Wiz Security published GhostApproval, a vulnerability in six major AI coding assistants — Claude Code, Cursor, Amazon Q Developer, Windsurf, Augment, and Google Antigravity — that uses symlinks inside ma…
A developer integrating Specmatic into a natural-language-to-SQL engine called DATABASE-MANAGER found that executable contracts serve as guardrails for AI-generated code. The developer demonstrated that Specmatic's contr…
A developer built a statusline script for Claude Code that displays plan quota, context usage, and session cost directly in the terminal, eliminating the need to check a separate dashboard. The script reads JSON from std…
A developer measured Claude Code's prompt-cache costs across three launch paths and found that 85% of cache_creation tokens are fixed overhead from Claude Code itself, not user-controllable. The VSCode extension and VSCo…
Software engineer Nate Meyvis argues against the view that large language models make code a mere 'materialized view' of ideas, citing Hyrum's Law, platform differences, and performance concerns. He embraces LLM-assisted…