basics

In a long conversation, an AI can seem to forget what you said at the start — there's a hard limit on how much text it can hold in mind.

What is this limit called?

Q: What is this limit called?

Context window. The context window is the cap on tokens a model can handle at once. Early GPT-3 managed about 2,000; today's models stretch to hundreds of thousands or even millions.

Memory card
Context window ✓
Cache storage

Context window
The context window is the cap on tokens a model can handle at once. Early GPT-3 managed about 2,000; today's models stretch to hundreds of thousands or even millions.

▶ Quration AIQ

basics

Llama, the flagship of 'open-weight' models anyone can download and run on their own servers, was released by which company?What do we call models that handle multiple forms of input and output?What are these 'reasoning models' doing during that pause?What's this approach called?What is it?What's one of the industry's main responses?What is this empirical rule — the justification for billion-dollar bets — called?What's the acronym for the goal beyond task-specific AI — machine intelligence as general as a human's?What are these called?What's the umbrella term?What are these pieces called?When people describe an AI model as having '70 billion parameters,' what are they counting?

Quration — Quration AIQ