A search engine takes an input string, a corpus of text, and returns a series of text that best comes next after the input string.
An LLM takes an input string a corpus of text, and returns a series of text that best comes after the next input string.
To get a paragraph of output, you run the search over and over again
Both the search and LLM reshuffle the inputs to the outputs.
If I'm describing the purpose of the LLM, it's got a wide number of usages. "Making my resume look more professional" or "be a crud api" or "reformat my ask into a api call to X service" or "give me a timeline of events surrounding Y with source links"
An 18 wheeler travels on wheels. A shopping cart travels on wheels. A shopping cart does not require a license to operate, therefore an 18 wheeler does not require a license to operate. A shopping cart can be operated inside a grocery store, therefore an 18 wheeler can be operated inside a grocery store. A child can operate a shopping cart, therefore a child can operate an 18 wheeler.
If I'm describing the purpose of an 18 wheeler, it's got a wide number of usages. "Carry my chicken" or "carry my lettuce" or "carry my Cheetos". Or, simply, "carry my groceries".
An LLM takes an input string a corpus of text, and returns a series of text that best comes after the next input string.
To get a paragraph of output, you run the search over and over again
Both the search and LLM reshuffle the inputs to the outputs.
If I'm describing the purpose of the LLM, it's got a wide number of usages. "Making my resume look more professional" or "be a crud api" or "reformat my ask into a api call to X service" or "give me a timeline of events surrounding Y with source links"