A developer writes the main text first. Then, the developer finds exact phrases from that text. These phrases are used for special tags.
By Pawan Nayar · from the LLOS AI Learning record
A developer writes the main text first.
Then, the developer finds exact phrases from that text. These phrases are used for special tags.
A developer writes the main text first. The developer does not think about 'essence' or 'feel_snippets' yet. After writing, the developer reads the text. The developer picks 3-5 short phrases for 'essence'. The developer picks up to 3 short phrases for 'feel_snippets'. These phrases must be exactly as they appear in the main text. The developer copies and pastes these phrases. The developer does not retype or change them. Each phrase must be found word-for-word in the main text. If a phrase does not match, the developer must fix it. The developer can change the phrase or change the main text.
A writer creates a lesson about AI. The writer finishes the main text. Then, the writer reads the text to find key phrases. The writer finds 'AI models learn from data' and 'user input guides AI'. The writer copies these phrases into the 'essence' field. The writer checks that these phrases are exactly in the main text. If a phrase is slightly different, the writer corrects it.
Resolved from this lesson's own record — real definitions, not invented for this page.
More from the same record, pulled by shared topic — not written new for this page.
An AI model often uses common labels for writers. These labels are called literary archetypes.
A developer should list all known problems. This includes bugs, which are errors in the code.
A developer uses the format ID 'mcq'. This format does not need an 'interaction_state'.
The 'subjective' format is a type of quiz. It lets the user type any answer they want.
A developer writes the main text first. Then, the developer finds exact phrases from that text. These phrases are used for special tags.