Most prompting advice focuses on structure. Templates. Formats. Roles. Those matter. But they're surface mechanics. The real skill is what you think about BEFORE you write the prompt. Second-Order Thinking is one framework. There are dozens more from investing, military
MACHINE LEARNING
-
Three-question prompt review to anticipate model outputs
By
–
The method is three questions. Use them before you hit send on any prompt. 1. "What's the most obvious output I'll get from this?" 2. "What happens after that output gets implemented?" 3. "What second and third-order effects should the model account for?" Add questions 2 and
-
AI models are literal first-order thinkers
By
–
AI models are first-order thinkers by default. You ask a question, they answer it. Directly. Literally. Without considering what happens next. That's not a flaw. That's how they work. The model responds to exactly what you give it. So if your prompt doesn't include the second
-
Ask the follow-up: improve generic AI outputs
By
–
"Why does my AI output sound so generic?" Because you're prompting at the surface. You ask for a strategy, AI gives you one, you move on. You never ask "and then what happens?" That one missing question separates average AI work from exceptional. And it has a name.
-
8B MoE Model Trained for Agentic Local Workflows
By
–
8B MoE (1B Activated) trained on 38 trillion tokens for local and agentic workflows
-
AI-Driven Agriculture System Automates Tomato Farming
By
–
#AI-Driven Agriculture System Plants, Monitors, and Harvests Tomatoes on Its Own
— Ronald van Loon (@Ronald_vanLoon) 29 mai 2026
by @sutoroveli_news#AgriTech #Innovation #Technology #TechForGood pic.twitter.com/WW1U6HO5Gr#AI-Driven Agriculture System Plants, Monitors, and Harvests Tomatoes on Its Own
by @sutoroveli_news #AgriTech #Innovation #Technology #TechForGood -
Unified Reinforcement Learning Framework for Humanoid Robots
By
–
Humanoid Robot Newly released a unified reinforcement learning framework for humanoid and quadruped robots!#humanoidtech #humanoid #robot #Robotics #AI #TechRevolution #TechInnovation #ArtificialInteligence #PhysicalAI@AlbertoEMachado @Eli_Krumova @postoff25 @Khulood_Almani… pic.twitter.com/ZLK38yfG0r
— Amitav Bhattacharjee (@bamitav) 29 mai 2026Humanoid Robot Newly released a unified reinforcement learning framework for humanoid and quadruped robots! #humanoidtech #humanoid #robot #Robotics #AI #TechRevolution #TechInnovation #ArtificialInteligence #PhysicalAI @AlbertoEMachado @Eli_Krumova @postoff25 @Khulood_Almani
-
LeJEPA World Model Learning Under Gaussian Latent Dynamics
By
–
New paper from Yann LeCun! "When Does LeJEPA Learn a World Model?" This paper proves that under Gaussian latent dynamics, LeJEPA can recover the hidden state behind nonlinear observations up to rotation. The intuition is that linear latent features are the most stable across
-
Shader test as a measure of AI coding capability
By
–
Except a shader like this is a very good measure of model capability because of the technical difficulty of building this sort of code. It translates to other coding as well. Feel free to see my many other tweets and substack posts (& book) about AI applications in businesses.
-
AI Models Understanding Chemical Principles
By
–
Building #AI models that understand chemical principles
by Anne Trafton @MIT Learn more: https://
bit.ly/4dtKrgb #ArtificialIntelligence #MachineLearning #ML