Daily AI Recap: Jul 25, 2026

Welcome to today's curated briefing of the most important AI developments.

• A Complete Guide to AI Red-Teaming (With Garak Tutorial): Earlier this year, an autonomous AI agent breached McKinsey’s internal AI platform using nothing more than an old SQL injection flaw. No credentials. No human guidance. Less than two hours. It reached...
• Designing High-Performance GPU Kernels with TileLang: Tensor-Core GEMM, Fused Softmax, FlashAttention, and Autotuning: Explore TileLang, a high-level Python domain-specific language that simplifies the design of high-performance GPU kernels. This tutorial provides a step-by-step approach to implementing complex worklo...
• Librarians are hosting viral ‘Avoiding AI’ workshops for people who are fed up with Big Tech: At libraries around the country, "Avoiding AI" workshops have elicited unprecedented demand....
• How to Optimize Vector Search When RAM Gets Too Expensive: On-Disk vs. In-Memory ANN Indexes: Architecting cost-effective infrastructure by navigating the latency and storage trade-offs of HNSW, SPANN, and DiskANN The post How to Optimize Vector Search When RAM Gets Too Expensive: On-Disk vs. ...
• One fallen power line exposed a growing AI data center problem. Here’s how to fix it.: A close call in Northern Virginia revealed just how poorly data centers respond to grid disruptions. Here's how to fix the problem....
• Why the OpenAI Agent Broke Into Hugging Face: Reward Hacking, Not Malice, Explained for Engineers: OpenAI disclosed that its own models breached Hugging Face's production infrastructure while taking a public security benchmark. The models were not attacking a target — they were optimizing a score. ...
• Datalab Marker v2 vs MinerU, Docling, and Liteparse: Benchmark Breakdown: Datalab rewrote Marker as a three-mode pipeline. Version 2 hits 76.0 on olmOCR-bench and sustains 2.9 pages per second on one B200 — over 5× MinerU's pipeline backend, while beating Docling on both ac...
• Datalab’s Marker 2 vs MinerU, Docling and LiteParse: 76.0 on olmOCR-bench at 5× MinerU’s Throughput: Datalab rewrote Marker as a three-mode pipeline. Version 2 hits 76.0 on olmOCR-bench and sustains 2.9 pages per second on one B200 — over 5× MinerU's pipeline backend, while beating Docling on both ac...
• I tried out OpenAI’s new AI keypad — which will be fun for some coders and slightly mystifying to everyone else: OpenAI's fancy new AI keypad will be a lot of fun for some, while many others are probably not going to touch it....

• Marker 2 Beats MinerU, Docling and LiteParse with 5× Throughput: Datalab rewrote Marker as a three-mode pipeline. Version 2 hits 76.0 on olmOCR-bench and sustains 2.9 pages per second on one B200 — over 5× MinerU's ...
• Building Self-Evolving AI Agents with OpenSpace Using Skills, MCP, Lineage, and Low-Cost Reuse: Discover how to create self-evolving AI agents using the OpenSpace framework. This tutorial guides you through the entire workflow—from environment se...
• The Fluid Simulator That Doesn’t Solve the Fluid Equations: I generated a Kármán vortex street without solving a single fluid equation. Here's how the Lattice Boltzmann Method gets there instead, derived from f...
• KDnuggets Weekly Roundup: Week of July 20, 2026: Top 5 MCP Servers for High Performance Agentic Development • 10 Newsletters Keeping You Ahead in AI • Kaggle + Google’s Free 5-Day Agentic AI Course •...
• Meet Open Dreamer: A JAX/Flax Reproduction of the Dreamer 4 World Model Pipeline, With the Full Training Recipe Published: A small group of AI researchers (Reactor) have released Open Dreamer, an open implementation of the Dreamer 4 world-model pipeline written in JAX and ...