Hi Reader, Over the past 50 tips, I’ve touched on many different topics: Python, Jupyter, pandas, ML, data visualization, and so on. Going forward, I’m planning to focus mostly on Artificial Intelligence. I’m announcing this so you know what to expect, and I know what to deliver! 💌 I’ll also try to make the tips shorter, so that they're easier to digest on-the-go. Finally, I plan to include an “action item” each week, so that you can practice what you’re learning. I hope you like these changes! But if it’s not for you, there’s an unsubscribe link at the bottom of every email. 👉 Tip #51: Experiment with LLMsYou’ve heard of ChatGPT, right? If you’re reading this newsletter, you’ve probably tried it out, and perhaps even use it on a regular basis. But what about Claude? Or Gemini? Or Llama? Or Grok? Or Nova? There are TONS of Large Language Models (LLMs), and it seems like every day a new one comes out. The choice is overwhelming, and so ChatGPT continues to be the market leader among both businesses and consumers, due in part to OpenAI’s superior brand recognition. Side note on terminology: OpenAI is the company behind ChatGPT, ChatGPT is the user interface (UI), and OpenAI offers models such as GPT-4o and o1-preview. In other words, ChatGPT is a UI for an LLM (not an LLM itself), but that distinction is unimportant in many contexts. Regardless of whether an LLM ever reaches Artificial General Intelligence (AGI), they're going to become an increasing part of our lives. As such, your future self will thank you for becoming comfortable with LLMs today, rather than waiting a few more years! 🏆 Which LLM is best?There’s no one model that is superior across all use cases. Rather, each model has its strengths and weaknesses, plus costs vary widely! Here’s the best model for each task according to my favorite AI newsletter, The Neuron (affiliate link): If cost and speed are a concern, here are The Neuron's top picks: 🧪 How to experiment with LLMsIf you find the lists above to be overwhelming, don’t fret! There’s no need to sign up for a bunch of LLMs right away. However, I would encourage you to at least start trying out LLMs and see how you feel about them. And with a bit of practice, you’ll begin to learn when they are useful and how to get the best results from them! ⏩ Action item: Try out Chatbot Arena. It’s free and doesn’t require an account. Here’s how it works:
This is a fun way to see how models vary, and learn if you have a preference for certain ones! Next week, I’ll show you an even better way to try out different LLMs!
See you next week! - Kevin P.S. How good are you at PowerPoint?​ ​ Did someone AWESOME forward you this email? Sign up here to receive more Artificial Intelligence tips! |
Join 25,000+ intelligent readers and receive AI tips every Tuesday!
Hi Reader, The Python 14-Day Challenge starts tomorrow! Hope to see you there 🤞 👉 Tuesday Tip: My top 5 sources for keeping up with AI I'll state the obvious: AI is moving incredibly FAST 💨 Here are the best sources I follow to keep up with the most important developments in Artificial Intelligence: The Neuron (daily newsletter) My top recommendation for a general audience. It’s fun, informative, and well-written. It includes links to the latest AI news and tools, but the real goldmine is...
Hi Reader, Before today’s tip, I wanted to give you a heads up: Tomorrow, I’ll be launching something brand new! Watch out for the announcement 👀 👉 Tip #53: How to get great results from AI models through prompting In the year after ChatGPT was released, I remember noticing two new trends: Articles about “prompt engineers” being hired for hundreds of thousands of dollars just to write prompts Endless guides promising to teach you the secrets of writing the perfect ChatGPT prompt My takeaway...
Hi Reader, Last week, I encouraged you to experiment with different LLMs, since there’s no one model that is superior across all use cases. Specifically, I suggested you try using Chatbot Arena, which allows you to chat with multiple models at once. It’s completely free, but has two significant disadvantages: Your chats are not private and may be used for research. It lacks the feature-rich interface provided by other LLMs. Today, I want to offer you a better method for experimenting with...