The Evaluation Loop: How AI Improves Its Own Output

The Evaluation Loop: How AI Improves Its Own Output

Feb 25, 2026 | Newsletters

⚖️ “With a leveraged worker, judgment is far more important than how much time they put in or how hard they work.” – Naval Hello Reader, AI is better at evaluating content than generating content.This makes sense, when you stop to think about it. For a large language model to interpret your instructions, and create output, all in the same step, it dilutes the same token budget over two requests.But if you have ask AI to evaluate its own outputs, it can focus all its attention on identifying…

Coaching LLMs: Get AI to Work Smarter for You

Coaching LLMs: Get AI to Work Smarter for You

Feb 18, 2026 | Newsletters

🌱 “A coach is just a placebo – it’s a commitment to make yourself a better person.” Barrett Brooks Hello Reader, Most people treat AI like a search engine. They ask simple questions and accept whatever it replies. But if you want truly great results, you need to stop being a consumer of AI and start being a coach to AI. In my next interactive workshop, you’ll learn how to train AI to think better, iterate on its responses, and refine its output—just like a great coach helps an athlete or…