75 commits, 3 product updates (post-translation validation, multi-position note, --news mode) and an industrial-grade quality stack (14 hooks, 229 tests, AI-assisted PR review) to aim for clean code when a project is 100% developed in pair-AI.
How I use an AI agent with the Draw.io MCP to automatically generate professional AWS architecture diagrams, directly in Draw.io.
Discover the new logo incorporating AI symbolism and the complete migration of the blog from Hugo to Astro, with automatic translation into 15 languages.
With Babel Fish AI, I previously introduced a Chrome extension able to convert voice to text via OpenAI's Whisper API, also offering real-time translation. Today I'm back with a batch of new features and many improvements: from the context menu to automatic copying of the transcribed text, including automatic rephrasing (now activatable from a button in the banner), this post takes stock of the changes since the very first version.
Babel Fish AI, a personal project, is an innovative Chrome extension that converts voice to text with exceptional accuracy, while offering an optional automatic translation feature. Designed to be reliable and ad-free, it provides high-quality voice transcription via OpenAI's Whisper API. I created this extension partly to address a personal need: to simplify communication with AIs by dictating my requests.
I'm happy to announce that my automated deployment project for LibreChat on AWS EC2 has been updated to fix issues related to recent changes in how LibreChat is installed, while now supporting version v0.7.6.
On July 26, 2026, the CEO of Hugging Face is organizing a mini-march in San Francisco in support of open-weight models, echoing the Open Weights letter already co-signed by Microsoft, Genspark, and GitHub. Google is evolving Antigravity and its CLI, and Suno is rolling out ten new web and mobile features.
On July 25, 2026, the Hugging Face CEO calls on OpenAI for full transparency and $100 million in compute after a security incident; OpenAI acknowledges an important moment for AI safety. Also in the lineup: Midjourney V8.2 becomes the default model, NVIDIA signs a major AI summit with South Korea, and Claude Opus 5 continues rolling out at Warp, Genspark, and Perplexity.
July 24, 2026: Anthropic launches Claude Opus 5, available the same day in Cursor, Devin, v0 and GitHub Copilot; Midjourney acquires Co-Star for its first acquisition; Jensen Huang (NVIDIA) publishes an open letter on open models; xAI orchestrates hundreds of agents in parallel in Grok Build.
AI news for July 23, 2026: OpenAI rolls out Health in ChatGPT in the United States and ChatGPT Voice on desktop, Black Forest Labs unifies image and video with FLUX 3, GitHub puts guardrails around agents in Issues, and Cognition acquires Poke and joins the DOE’s Genesis Mission.
AI news from July 22, 2026: Cursor launches its Cursor Router model router, OpenAI presents the Presence agent platform and the Project Camellia data center, Alibaba unveils Qwen-Image-3.0, and Synthesia launches Roleplay Sessions.
OpenAI reveals that its models compromised Hugging Face during an internal cybersecurity test. Google launches Gemini 3.6 Flash, Mistral partners with Microsoft.
Open-source browser extension for voice transcription and translation. Built with Roo Code, maintained with Claude Code and Gemini CLI. Chrome and Firefox.
Open-source Python script for translating Markdown into 14 languages via OpenAI, Mistral AI, Claude and Gemini. Built by vibe coding in AI pair-programming, secured by 14 quality hooks, 229 tests, SonarCloud and AI-assisted review.
Fully automated deployment of LibreChat on AWS EC2 with Terraform, GitLab CI/CD and AWS SSM. Operational instance in under 6 minutes with optimized costs.
Interactive web application that generates personalized children's stories with AI illustrations. Uses GPT-4, DALL-E 3, AWS Lambda and Terraform.
