How Does GPT-4 Know When to Stop Generating?

How LLMs Know When they have answered your question?

Good morning everyone! In this iteration, I wanted to answer a "simple" question I asked myself: how does GPT know when to stop its answer? How does it know it has given a good enough answer? How does it stop talking?

Two scenarios can make the model stop generating: ‘EOS tokens’ (<|endoftext|>) and ‘Maximum Token Lengths.’ That's what this week's video (or article version) answers:

And that's it for this iteration! I'm incredibly grateful that the What's AI newsletter is now read by over 16,000 incredible human beings. Click here to share this iteration with a friend if you learned something new!

Looking for more cool AI stuff? 👇

• Looking for AI news, code, learning resources, papers, memes, and more? Follow our weekly newsletter at Towards AI!

• Looking to connect with other AI enthusiasts? Join the Discord community: Learn AI Together!

Want to share a product, event or course with my AI community? Reply directly to this email, or visit my Passionfroot profile to see my offers.

Thank you for reading, and I wish you a fantastic week! Be sure to have enough sleep and physical activities next week!

Louis-François Bouchard