Training for Chat AI

In order to access its intelligence sometimes you have to talk to it as if it were an idiot. Or perhaps an idiot savant.

Anyone can use ChatGPT. Just go to chatgpt.com and you can access the most recent versions, GPT-4o, and o1, for free (there are some premium features available for an extra $20/month).

When you go to ChatGPT you find essentially a blank screen and the question “How can I help you today?”

You can ask it questions. Better still, you can upload a large PDF and ask questions of the file. You can also upload images, which it can describe, or a scanned page: it can recognize the text, even if handwritten.

Learning how to ‘speak’ with Chat AI has become an essential skill for everyone using today’s Chat AI. You can literally speak to Chat AI in the latest mobile versions, but prompting is a special kind of language, and initially feels unnatural. Users discover that the more precise and detailed their prompts are, the better the responses they receive from ChatGPT. Further, prompts are not just one-off. Chat AI can continue a conversation for quite a while, and if you don’t get the answer you’re looking for you can revise and refine your prompts. This takes a lot of getting used to, and has spawned a series of how-tos, written and online, to train users on how to get the most out of prompting.

Try asking any of the Chat AI software to explain a concept like developmental editing. Then ask it to craft an explanation that a 12-year-old could understand. The results are dramatically different. Amusingly, Chat AI seems also to respond to emotional pleas. Adding “this is very important to my career” to a prompt can coax more useful responses.

(It’s both reassuring and deeply troubling that the top scientists working on language-based AI are unable to explain why things like this occur.)

Just now I asked ChatGPT to list “the top 4 elements of effective prompting”:

1. Specific task instruction: Say exactly what you want the model to do.
2. Relevant context: Provide every fact, excerpt, or data point the model should rely on—don’t make it guess.
3. Clear role/voice—Assign a persona or perspective (“You are an acquisitions editor…”) to set the tone and expertise.
4. Output format & constraints: Tell the model how the answer should look (structure, length, citation style).

In a sense it’s quite odd: AI has a good grasp of language—shouldn’t it have a sense of what you mean without pedantic prompting? But it’s precisely that mastery of language that makes prompting most powerful. Tell it exactly what you mean, not approximately—Chat AI understands complex instructions, in fact it thrives on them.

Talk to it like the helpful assistant, or the counselor, that you want it to be, not like a kid off the street.

The takeaway here is that, at least for the time being, the effective use of LLM-based AI tools requires conversancy with prompting best practices. A prompting mastery will be appropriately rewarded.

I’m going to include two links to prompting guides that can help you go a few steps deeper. Beware: The rules for prompting change as the software evolves, and a guide from 2023 is mostly by now misleading. These two were written or revised in April 2025:

1. Prompt Engineering (Montana State University Library)
2. Prompt engineering guide: IBM