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