LLMs are a pretty good tool to summarize any subject, or present it with different words or in a different approach… They are a statistical word predictor tool after all.
So yeah, if you understand that LLMs:
don’t possess intelligence;
they are just reproducing patterns from the training material used;
it’s impossible for them to contain ALL “knowledge” from the training material;
the “context” provided directly influences the response
Then, I’d say that LLMs can be used as a very good facilitator to learn about almost any subject that has already been documented in any word format in almost any language.
It feels like as the models were iterated on they got worse at it over time. I wonder if it’s because of all the guard-railing and internal censorship etc.
It’s just a messy process, it’s purely based on probability, I don’t think it’ll ever get good, people were just being lied to. Don’t forget that they relied on “confirmatory bias” and “selection bias” from the users as well.
I have never used a LLM to write any of my comments on the internet, neither here nor in any social network I have an account.
And about the bullet points, in places that accept MarkDown similar syntax I tend to use bullet points because it’s a feature that helps lay out the ideas in a good formatting for the reader when there’s enumerations, lists, or similar things involved.
But yeah, you will never find comments of mine in, lets say, Instagram, with bullet points, because the editor of the app there sucks, you would have to type your comment in a external app which creates the bullet points characters already in a newline (you cannot even normally break lines in Instagram comments lol, it’s really unsanitary haha), and I ain’t gonna do that.
LLMs are a pretty good tool to summarize any subject, or present it with different words or in a different approach… They are a statistical word predictor tool after all.
So yeah, if you understand that LLMs:
Then, I’d say that LLMs can be used as a very good facilitator to learn about almost any subject that has already been documented in any word format in almost any language.
They’re not even good at that.
It feels like as the models were iterated on they got worse at it over time. I wonder if it’s because of all the guard-railing and internal censorship etc.
It’s just a messy process, it’s purely based on probability, I don’t think it’ll ever get good, people were just being lied to. Don’t forget that they relied on “confirmatory bias” and “selection bias” from the users as well.
your bulleted list has me suspecting you used an llm to write this. TRAITOR
I have never used a LLM to write any of my comments on the internet, neither here nor in any social network I have an account. And about the bullet points, in places that accept MarkDown similar syntax I tend to use bullet points because it’s a feature that helps lay out the ideas in a good formatting for the reader when there’s enumerations, lists, or similar things involved.
But yeah, you will never find comments of mine in, lets say, Instagram, with bullet points, because the editor of the app there sucks, you would have to type your comment in a external app which creates the bullet points characters already in a newline (you cannot even normally break lines in Instagram comments lol, it’s really unsanitary haha), and I ain’t gonna do that.