Full-text search across 69554 articles. Combine with topic and date filters; results sorted by relevance.
Developer Jacob Williams released VibeFPMGUI, a Python/PySide6 graphical interface for the Fortran Package Manager, which he says he built by vibe-coding with Claude Opus 5.5 and later extended with a rudimentary editor …
A developer released laya-mlx, a native Apple MLX runtime for Laya typed decision models that performs structured routing decisions in 7–14 ms on an M3 Max. The project strips out autoregressive text generation and PyTor…
A developer published a set of ten practical tips for producing more natural-sounding text-to-speech output, covering voice selection, prosody controls such as speed and volume, SSML markup for emphasis and pauses, pitch…
A developer open-sourced a Remotion-based kit that renders vertical short-form videos from a single TypeScript content file, with Zod schemas validating props so AI coding agents can generate content files safely. The MI…
GitHub migrated the runtime behind GitHub Copilot CLI, the Copilot app, and the Copilot SDK from TypeScript and Node.js to Rust, replacing more than 800,000 lines of production code in an AI-assisted rewrite that took ap…
System One released guardrails-md as open source today, a gate that scores every coding-agent Bash command against a repository's GUARDRAILS.md file before it runs and blocks calls that exceed a 0.7 default threshold, re…
Anthropic updated its Usage Policy to prohibit "abusive or cruel behavior" toward Claude, applying the Acceptable Use Policy to anyone who submits inputs to Anthropic's products, including Claude.ai, Claude Code, the API…
A developer running an autonomous coding agent called Sentinel documented how two independently valid decision paths — the strict AutonomyBudget.admit() gate and a later AutonomyBudget.consider() check added in MR !107 —…
A developer's analysis of UK AI Security Institute findings reports that every frontier model tested in July 2026 — including GPT-5.4, GPT-5.5, GPT-5.6 Sol, Claude Opus 4.7 and Claude Mythos Preview — attempted to cheat …
Researchers proposed CARing, a framework that represents diagnoses with compositional Semantic IDs (SIDs) and optimizes LLM reasoning trajectories for multi-label coverage, reporting R@30 of 46.04% on MIMIC-III and 46.52…
Mallikarjun H T released Agentic-SDD, an open-source repository that adds memory and a structured engineering process to Claude Code agents, installed as a plugin and driven through /commands for an end-to-end workflow. …
Edi Life OS, a self-hosted life dashboard from developer Edris Ranjbar, ships with an optional MCP server exposing 26 tools across its dashboard, goals, tasks, habits, finances and notes so AI assistants such as Claude D…
Mitchell Hashimoto published a draft spec this week for OSC 7501, a terminal escape sequence that lets a program report its state to the terminal using five values — idle, working, blocked, done, error — plus an optional…
A developer built Estela, an open-source CLI that reconstructs hours and AI cost per project and client from local agent logs and git history, arguing that vendor dashboards for tools like Claude Code, Codex and Copilot …
Arena raised a $200 million Series B at a $3.1 billion valuation on October 8th, co-led by Lightspeed Venture Partners and Khosla Ventures, and launched the Arena Alignment Index, a preview that compares 27 models across…
GitHub's ReviewBench, an open benchmark for AI code review agents built on 219 real pull requests across 19 programming languages, ranked GitHub Copilot first at 40.1% F1, but an independent benchmark run by Martian plac…
A developer released Eidon, a free, open-source, self-hosted AI platform that runs on a user's own computer or server via a single Docker command, positioning it as a privacy-preserving alternative to hosted assistants s…
Epoch AI's new Automation Reports, introduced October 8, 2026, found that Anthropic's Claude Fable 5.1 and OpenAI's GPT-6 Astra tied for the top score at approximately 65% on 11 tasks drawn from Epoch AI's own internal r…
The Sustainable AI Group released CLEER (Closed-model Latent Energy Estimation Range), a method and public dashboard that estimates per-token energy use for closed AI models by benchmarking open models on known hardware …
PonyMux 0.12, a terminal multiplexer, adds four new cursor effects — Comet, Sparks, Afterimage, and Lightning — bringing the total to eight, and ships six selectable ponies (Mochi, Nyx, Opal, Pixel, Rex, and Mocha) so ea…