Google ruling LLM 101:

chatbots now routinely incorporate into their responses fresh information from the internet or other sources through a process known as grounding

before, an LLM’s response was time-limited by the end date of its training data…through grounding an LLM can now access content beyond its training data, such as web pages in a search index, to provide more recent and more accurate information

pre-training creates a base (or foundation) model, which is then post-trained (or fine-tuned) on collections of data so that the base model can perform specialized tasks