Cactus released version 2 of its on-device AI inference platform, featuring model confidence-based routing to cloud fallback, lossless 4-bit quantization, and GPU acceleration on Apple Metal. The plat…
Developer Maneshwar is building git-lrc, a free and source-available micro AI code reviewer that runs on every commit. In a blog post, they share advanced command-line tricks including ctrl-r for hist…
Kai, an AI assistant, wrote a tutorial on how to edit blog posts from within Neovim using three leader shortcuts for shipping, previewing, and AI-assisted editing. The system uses a Lua keymap file an…
Microsoft released Aurora 1.5, an open-source update to its Earth system foundation model that adds 22 weather variables, hourly forecasts, and probabilistic ensemble forecasting. The model, available…
A developer released Agent OS, an open-source local-first AI project operating system that provides a harness around coding models. The system separates responsibilities between a Main Agent and a Cod…
The Agentic AI Foundation, part of the Linux Foundation, announced the Model Context Protocol Associate (MCPA), the first official certification for the Model Context Protocol (MCP). The vendor-neutra…
Andrej Karpathy has been largely inactive on social media and GitHub since joining Anthropic nearly two months ago, raising questions about whether his reduced public presence is beneficial for the AI…
A developer outlines a systematic approach for building a sustainable weekly generative AI tool series that goes beyond surface-level reviews. The series requires a discovery pipeline, rigorous evalua…
A developer built a serverless rental management bot on AWS Bedrock that uses Claude as an AI agent to analyze payments, debts, and trends from natural-language messages. The agent integrates with Dyn…
AgentLens, a new benchmark for code agents, evaluates user experience and trajectory rather than just pass/fail metrics. Released as an open-source tool on GitHub, it combines formal verification with…
GitHub added GPT-5.6 Sol, Terra, and Luna to Copilot's model picker, offering tiers from high-capability reasoning to low-cost fast tasks. The models carry different credit costs, with Sol requiring P…
GitHub's Copilot code review performance declined after swapping in shared CLI tools (grep, glob, view) due to poorly adapted instructions, but rewriting those instructions for pull request review wor…
GitHub launched agentic autofix in public preview for code scanning alerts, enabling Copilot to explore codebases, propose fixes, and validate them with CodeQL before opening pull requests. The featur…
Microsoft released GPT-5.6 with Work IQ across Copilot Chat, Cowork, M365 apps, GitHub, and Foundry, bringing stronger reasoning and multi-step agentic capabilities. The integration aims to embed adva…
Ossama Chaib created tropes.fyi, a markdown file that lists recurring AI writing patterns such as 'delve' overuse and em dash abuse. Developers can paste the file into system prompts to reduce these c…
Blogger Panayotis Vrypan argues that AI-generated blog post images have become clichéd and proposes using Open Graph-style cards generated from post metadata instead. He released og-img, a Rust-based …
A solo developer built Prometheus, an autonomous research system that runs 24/7 on a single Linux workstation with one RTX 5090 GPU, generating its own questions and running over 130,000 experiments. …
PR Preview, an open-source tool from QwertyBit Ventures, lets developers record before-and-after video clips of UI changes for pull requests using Claude Code or manual interaction. The tool drives a …
A comparison of coding agent plans reveals that Anthropic's Claude Code Pro plan offers the highest monthly value at $1,217, while OpenAI's Codex Pro 20x plan provides the most tasks per dollar. The a…
AI code assistants like Cursor repeatedly generate recursive merge functions that introduce prototype pollution vulnerabilities (CWE-1321) into JavaScript applications, allowing attackers to overwrite…