Intro to llm augmentation #71
Open
+37
−0
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Habeebah157
reviewed
Nov 28, 2025
|
|
||
| This is why hallucinations happen: the model fills gaps with confident guesses, misremembers facts, or invents details that fit the conversation. Even when the model is trying to be helpful, it may prioritize what it thinks you want to hear over what is actually correct. And because LLMs are trained on data from the past, with a fixed cutoff date, they rapidly fall out of sync with current information. | ||
|
|
||
| When we want an LLM to behave more like a truth-tracking assistant rather than a storyteller, we need to augment its knowledge. Over the last few years, three main approaches have emerged: prompt engineering, fine-tuning, and retrieval-augmented generation (RAG). Each approach has its place, and professional AI systems often use more than one. If you want an LLM to be more truthful, more up-to-date, and more grounded in real data, these are the tools you will reach for. |
Collaborator
There was a problem hiding this comment.
" If you want an LLM to be more truthful, more up-to-date, and more grounded in real data, these are the tools you will reach for."
I think this part could be rephrased because I do not understand it
Collaborator
Author
There was a problem hiding this comment.
" If you want an LLM to be more truthful, more up-to-date, and more grounded in real data, these are the tools you will reach for." I think this part could be rephrased because I do not understand it
Thanks that is helpful -- I will expand on that!
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Intro for week 2 of AI module: closes out #62