Michael Taylor is a freelance prompt engineer. He explores how to manage AI tools like humans in his monthly column, Also True for Humans.
Using ChatGPT and Claude for memetic analysis
I tested 12 AI models on real human behavior—the best one costs less than a penny per 100 responses
Evals are often all you need
The next generation of AI is coming—here’s how they work
Provide examples to your LLM with few-shot learning
Understanding AI's blind spots can make you a better decision-maker
AI engineer and Every columnist Michael Taylor recently stopped by our New York office for a tutorial on how the prompt optimization tool works
Know when to copy—and when to go against the grain
Prompting AI tools is a new form of management science
My AI experiment hit 60 percent accuracy—not perfect, but enough to change how we think about market research
Why role prompting your LLM yields the response you want
Repeat AI tasks with self-consistency sampling to get better results
I shouted at my AI coworker—and it worked
Here's what they said (and how you can ask them, too)
AI agents cosplaying as online commenters have a lot to teach us
How LLMs will beat the best human marketers
Solving AI hallucination with retrieval augmented generation
How chain of thought works to get better responses
.png)
.png)
