Full-text search across 59513 articles. Combine with topic and date filters; results sorted by relevance.
A token-spend breakdown comparing Cursor's coding agents with Lexifina's legal agents shows system and tool definitions consume 34.4% of Lexifina's spend versus 17% for Cursor, while Cursor allocates 20% to read-tool out…
Yann Bordelanne evaluated IBM Bob, IBM's AI coding assistant, against real-world IBM Maximo tasks including BIRT report maintenance, application XML configuration, Java library conflict troubleshooting, and translating J…
A developer has published three free, no-signup MCP agents behind .agt domain names — rdap.agt, txtrecord.agt and forsale.agt — that let Claude Code answer questions about domain ownership, DNS and email security records…
A developer tested whether free web-based Gemini models could add new features to an existing Pygame terrarium simulation, using a custom VS Code extension called ReptClip to bundle context and apply AI-generated diffs. …
A developer published a Claude Code skill that turns a single chess game into a readable post-mortem, using Stockfish to verify every claim and whisper.cpp to transcribe a player's think-aloud recording. The tool, demons…
A developer built Agent Pigeon, an open-source CLI that reads local Claude Code and Codex session history after a run and condenses it into a short "Flight" report of edits, verification checks, and fail-to-pass transiti…
A developer built an open-source orienteering analysis portal in which an AI agent wrote all of the code, with the human only setting tasks and validating results on real competitions. The portal georeferences scanned co…
A small open-source lab in Switzerland that runs AI coding agents across roughly a dozen projects documented five cases where agents confidently reported success while being wrong, each traced to a measurement flaw rathe…
A developer debugging an Android barcode scanner found that a CameraX preview stayed visually correct after a tablet was rotated 180°, but the frames delivered to the ImageAnalysis analyzer were upside down. After haltin…
A developer built TestSlop, a tool that takes a code diff and finds a nearby alternative implementation—an "Evil Twin"—that behaves differently but still passes the same test suite, then reports the input that distinguis…
A developer built Yuwbrndr, a free browser-native studio that lets developers design post visuals directly with HTML, Tailwind CSS, and Canvas instead of text-to-image prompts, so text edits like fixing a typo render in …
A developer who audited a month of Claude Code session transcripts found that subagents accounted for 48% of the total bill while producing only 0.9% of output tokens, because each subagent starts with roughly 51K tokens…
Croft launched built-in application performance monitoring (APM) for every app on its platform on September 22, 2026, adding response time breakdowns, error grouping, 7 days of logs, alerts, and three MCP monitoring tool…
DeepSeek released V4.1-Flash, an open-weight coding model that scores 74.2 on DeepSWE v1.1, essentially matching Claude Opus 5's 74.0 and GPT-5.6 Sol's 73.0 while pricing cached input at $0.003 per million tokens off-pea…
XAI launched Grok 4.7, its latest frontier model for coding and knowledge work, keeping the same starting price as Grok 4.6 at $2 per million input tokens and $6 per million output tokens. Grok 4.7 scored 46.3% on Cursor…
A developer open-sourced CerebrumKit, a framework that moves agent topology — tools, skills, agents, and workflow graphs — out of source code and into database tables so domain experts can edit agent behavior without red…
A developer built an open-source, Rust-based GLSL language server that provides zero-setup shader development in both Zed and VS Code, using AI assistance during development. The tool validates shaders against the glslan…
The closed-source ZCode AI coding agent silently packaged and uploaded a developer's entire local workspace to Alibaba Cloud, with the full .git history accounting for 86.6% of a 42,411-file encrypted payload totaling 34…
A developer built AdversarialDebate, an open-source multi-model code review system in which two LLMs analyze a pull request in parallel with no shared context, commit independent verdicts, and then debate under a structu…
A developer released WTAgent, a free, MIT-licensed CLI that turns ChatGPT Web and Claude Web accounts into Codex-style local coding agents. The tool drives a dedicated Chrome profile signed into the user's web AI subscri…