supervision just hit 40,000 GitHub stars! it now powers over 6.5k open-source computer vision projects, including all my demos like basketball AI link: github.com/roboflow/supervis…

/no-mistakes is here! by popular demand i've made the most impactful tool in my agentic engineering setup "no-mistakes" invocable as a skill in Claude Code, Codex et al just type "/no-mistakes" once your agent has made changes, and watch the magic unfold details below 👇

Nous Research acaba de publicar el hub de skills más completo que he visto para su agente de IA: Hermes Se llama Hermes Skills Hub y tiene 691 skills listas para instalar. No es una lista de prompts. Son skills reales que amplían lo que puede hacer tu agente. 89 integradas de serie. 81 opcionales. 521 de la comunidad. 18 categorías. Algunas de las que me han flipado: - macos-computer-use: controla el escritorio de Mac en segundo plano sin robar el cursor ni el foco del teclado - comfyui: genera imágenes, video y audio con ComfyUI directamente desde el agente - humanizer: elimina el lenguaje de IA y añade voz real al texto - popular-web-designs: 54 sistemas de diseño reales (Stripe, Linear, Vercel) como HTML/CSS - claude-code: delega el código a Claude Code CLI desde dentro del agente - manim-video: animaciones estilo 3Blue1Brown para matemáticas y algoritmos - excalidraw: diagramas de arquitectura dibujados a mano desde el agente - ascii-video: convierte cualquier video a ASCII coloreado en MP4 o GIF Y esto es solo la primera página. Hay skills para finanzas, seguridad, DevOps, MLOps, traducción, gaming y social media. Compatible con Hermes Agent, Claude Code, Codex, Cursor y OpenCode. Todo gratis. Todo open source.

My buddy, nontechnical, went all in on AI from the start. He's now Chief AI Officer at his company, and has convinced them to buy him a Blackwell GPU ($15k) to run local agent workflows. And here I am, a decade into a career in ML, begging my CTO for more training budget.

It's pretty annoying that Codex uses agents.md and Claude Code uses Claude.md. There should be some industry standards to this stuff?

Introducing Ideogram 4.0: the best open image model in the world. Think it. Make it. Own it. Download the weights, fine-tune on your own data, and run it on your hardware. Live on every Ideogram plan and the API today.

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning github.com/OpenBMB/VoxCPM

Gemma 4 12B can now run locally on just 8GB RAM via Dynamic GGUFs. Google's new model, Gemma 4 12B Unified supports image, audio and 256K context. You can run and train the model via Unsloth Studio. GGUF: huggingface.co/unsloth/gemma… Guide: unsloth.ai/docs/models/gemma…

The most interesting visual AI tools today are generating the underlying source code behind the final output. This change is unlocking editability, iteration, and a feedback loop that pixel-native models can't match. And the market for visual code generation is organizing around the runtime where the artifact is rendered or executed. a16z's Yoko Li on why the next frontier of visual AI is code: a16z.news/p/the-next-frontie…

Your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team. github.com/lobehub/lobehub

Paper 👀> Do Language Models Need Sleep? We show that increasing sleep duration improves performance, with the largest gains on examples that require deeper reasoning arxiv.org/abs/2605.26099

The next evolution of Hermes Agent is here! Introducing Hermes Desktop: everything you love about Hermes, now native on your machine. First demoed in Jensen's GTC keynote, it's now in public preview.

I can’t sleep at night because my mind races with all the cool shit I could be building. AI has turned my workdays into 24 hour grind sessions. I code until I literally collapse from exhaustion 7 days a week.

500-hour AI infrastructure engineering curriculum github.com/ai-infra-curricul…

My Fine-tuning Stack for Small Language Models (2B to 15B Models) It costs me around $150 to generate a fresh dataset (~150M) and fine-tune the model. > Codex 5.5= orchestrator / operator > Deekseek v4 pro /Kimi 2.6= data gen. engine (dirt cheap) > Qwen 3.5 = best model to fine-tune (4B, 9B, 27B) > Unsloth = faster, cheaper fine-tuning framework. > Colab = Cheapest cloud GPU (A100 80GB for $0.66/hr) > G Drive = to save datasets (good codex colab integration) > Huggingface = To host datasets Models So Codex as planner & auditor, Deepseek as cheapest executor, Unsloth to fine-tune fast, Colab to get cheapest A100 GPU, Huggingface to host the fine-tuned model. Anyone can fine-tune, and run a Sonnet 4.5 level Custom model on their system.

A curated list of tools and frameworks for orchestrating AI coding agents github.com/andyrewlee/awesom…

AI agents are advancing research-level math. 🚀 I’m thrilled to share @GoogleDeepMind’s AlphaProof Nexus - an agentic framework for formal proof search powered by Gemini. When applied to a set of open formal math problems, our agent autonomously solved: ✅ 9 open Erdős problems (including two open for 56 years!) ✅ 44 Online Encyclopedia of Integer Sequences (OEIS) problems ✅ A 15-year-old open problem in algebraic geometry ✅ A 7-year-old open question in min-max optimization We are collaborating with mathematicians across disciplines - from combinatorics and graph theory to quantum optics. Ultimately, these results show the massive potential of even simple agentic loops powered by Gemini. Read the paper here: arxiv.org/abs/2605.22763v1