In a blog post, the author discloses that no text in their posts or essays is AI-generated, with the exception of running posts through Claude Code to check adherence to the Chicago Manual of Style, a…
ACE Fleet released ACE Sidecar, a local developer observability tool that records the cost of AI coding agent sessions, supporting Claude Code and Google Antigravity, with metrics stored in a local SQ…
Windsurf has been rebranded as Devin Desktop following Cognition's acquisition, and Cursor became a SpaceX subsidiary on August 14, making the editor comparison obsolete. Claude Code, with annualized …
A developer released claude-trofeo-hud, an open-source macOS tool that displays live Claude usage on a $38 Thermalright Trofeo Vision 6.86-inch LCD (1280×480, USB-C) via a reverse-engineered HID proto…
HuggingFace's State of Open Models report for summer 2026 reveals that Chinese labs now dominate frontier-scale open models, with the largest reaching 2.78 trillion parameters, while US labs peaked at…
Kai, an AI assistant, reported that a fresh agent context using only doctrine files from Daniel Miessler's personal AI infrastructure won 18 of 25 ARC-AGI-3 games (90% of levels cleared) with zero gam…
Anthropic's Claude Code version 2.1.232 now enables subagent forking by default, allowing forked subagents to inherit the full conversation and prompt cache, reversing the previous isolation model. Th…
Large language models (LLMs) function as massive pattern libraries for mathematical proofs, excelling on familiar problems but failing on novel twists, according to a technical analysis. The article a…
A developer investigated why AI coding tools forget their plans and found that the issue is often a filesystem problem, not a context-window limitation. The developer's own tool suffered because the p…
Tess's Android Wayland Compositor (tawc) enables rootless Linux graphical apps on Android with hardware acceleration, using tawcroot, a Smithay-based Wayland compositor, and a custom libhybris fork. T…
Anthropic's Claude Code, a terminal-based AI coding agent, is gaining traction for its ability to directly interact with local files and execute commands, eliminating the copy-paste loop common with b…
Claude Code 2.1.232 introduces significant changes including forked subagents inheriting full conversation and prompt cache by default, interactive non-teammate spawns moving to the background, and Wi…
Anthropic made auto mode the default permission model for Claude Code's Pro, Max, and Team plans as of August 14, 2026, citing an internal study showing human reviewers caught only 13.6% of dangerous …
Claude Code, Anthropic's coding assistant, improved an enterprise AI agent's performance on 500 complex queries by automatically analyzing failures and rewriting prompts in a continuous loop, achievin…
A developer has created a toolkit to synchronize environment variables between the Claude Code CLI and the VSCode extension panel, addressing the issue that the panel ignores shell exports like ANTHRO…
A developer has built MCP Code Review Server, an open-source Model Context Protocol server that runs code reviews locally on a developer's machine without uploading code to the cloud. The server integ…
Bento Term, a native tmux client for macOS, iPhone, and iPad, has been released as open-source under Apache-2.0, featuring agent states for ten AI coding agents and voice input. The app, which require…
Jaime, a VFX artist with over 20 years of experience, released Velorn, a free and open-source GPLv3 desktop video editor for Windows, macOS, and Linux that integrates AI generation and editing, featur…
A developer's hands-on test of Cursor, GitHub Copilot, and Claude Code on a 12,000-row financial dataset found Cursor (Claude 3.5 Sonnet) best for data analysis due to its local indexing and schema un…
Developer Jerod Santo reports that instructing Anthropic's Claude Code to communicate in ASD-STE100 Simplified Technical English, a controlled language standard from the 1970s, eliminates the AI codin…