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