Tip #59: Get good at today's AI models quickly 💨

Hi Reader,

In this week’s tip, I’ll be breaking down some highly practical advice for taking full advantage of the capabilities of today’s AI models.

Check it out below! 👇

Today’s tip is based on Ethan Mollick’s excellent article, Using AI Right Now: A Quick Guide.

I recommend reading the whole thing if you have time, but if not, I’ve pulled out some important quotes from the article and added my own commentary:

For most people who want to use AI seriously, you should pick one of three systems: Claude from Anthropic, Google’s Gemini, and OpenAI’s ChatGPT.

Agreed - these are the models I use.

With all of the options, you get access to both advanced and fast models, a voice mode, the ability to see images and documents, the ability to execute code, good mobile apps, the ability to create images and video (Claude lacks here, however), and the ability to do Deep Research. Some of these features are free, but you are generally going to need to pay $20/month to get access to the full set of features you need.

As I’ve mentioned previously, I access models via API using TypingMind, and thus I pay based on token usage. I admit I’m not a heavy user, but I’ve spent less than $5 this year, which is way less than $20 per month AND I still get to use any model I like!

*Model comparison (image) by Ethan Mollick*

ChatGPT, Claude, and Gemini each offer multiple AI models through their interface, and picking the right one is crucial… The casual models are fine for brainstorming or quick questions. But for anything high stakes (analysis, writing, research, coding) usually switch to the powerful model.

This is exactly my strategy: Since I pay more (per token) for the better models, I use them only when the stakes are higher or when the cheaper models aren’t producing satisfactory results.

*Deep Research (image) by Ethan Mollick*

Deep Research is a key AI feature for most people, even if they don’t know it yet. Deep Research tools are very useful because they can produce very high-quality reports that often impress information professionals (lawyers, accountants, consultants, market researchers) that I speak to… Deep Research reports are not error-free but are far more accurate than just asking the AI for something, and the citations tend to actually be correct.

Agreed - Deep Research can put together a seriously impressive report, though it’s currently only available via the web interface (not the API).

It used to be that the details of your prompts mattered a lot, but the most recent AI models I suggested can often figure out what you want without the need for complex prompts… So just approach the AI conversationally rather than getting too worried about saying exactly the right thing.

Agreed, though he does offer some basic prompting advice:

Give the AI context to work with: Most AI models only know basic user information and the information in the current chat, they do not remember or learn about you beyond that.

Be really clear about what you want: Don’t say “Write me a marketing email,” instead go with “I’m launching a B2B SaaS product for small law firms. Write a cold outreach email that addresses their specific pain points around document management. Here’s the details of the product: [paste]”

Ask for a lot of things: The AI doesn’t get tired or resentful. Ask for 50 ideas instead of 10, or thirty options to improve a sentence.

Two Way Conversation: You want to engage the AI in a back-and-forth interaction. Don’t just ask for a response, push the AI and question it.

There’s much more in this guide, and so I recommend reading the whole thing!

I hope you enjoyed this week’s tip!

- Kevin

P.S. Beat the AI to keep your job

Learn Artificial Intelligence from Data School 🤖

Tip #59: Get good at today's AI models quickly 💨

Top AI news: Mental Health edition 🧠

Tip #60: Run AI models locally (it's private & free!)

Top AI news: AI teaches your kid, LLMs send secret messages, AI makes you a TV star 🤩