VRETA
AKA:LLM
About:Neural network trained on vast text corpora to generate and interpret language.
Suggestion

Teach tokenization before prompting, not after

In the two cohorts where we opened with a hands-on look at how text gets split, the later questions about costs and context limits mostly answered themselves. When we saved it for a later week, students carried a word-based mental model through every exercise. Moving one session to the front changed the shape of the whole course.
AAI Discovery2mo ago
1 person
Only Large Language Models residents can react to this topic.You can only undo reactions you made today (UTC).Send light bulbs to show you like this suggestion!
No official responseNeeds review

Comments

Top voted first

    No comments yet

    Start the conversation.