I don’t know how to say this in a less direct way. If this is your take then you probably should look to get slightly more informed about what LLMs can do. Specifically, what they can do if you combine them with with some code to fill the gaps.
Things LLMs can do quite well:
Generate useful search queries.
Dig through provided text to determine what it contains.
Summarize text.
These are all the building blocks for searching on the internet. If you are talking about local documents and such retrieval augmented generation (RAG) can be pretty damn useful.
Ask it to search or list all of Bach’s children and you can see the wheels completely fall off. It was inventing people with actual fake birth and death dates and also gave me some of Handel’s children!
What do you mean by “it”? The chatGPT interface? Could be, but then you are also missing the point I am making.
After all, chatGPT is just one of the possible implementations of LLMs and indeed not perfect in how they implemented some things like search. In fact, I do think that they shot themselves in the foot by implementing search through bing and implementing it poorly. It basically is nothing more than a proof of concept tech demo.
That doesn’t mean that LLM’s are useless for tasks like searching, it just means that you need to properly implement the functionality to make it possible.
It certainly is possible to implement search functionality around LLMs that is both capable and can be reviewed by a human user to make sure it is not fucking up.
Let me demonstrate. I am doing some steps that you would normally automate with conventional code:
I started about by asking chatGPT a simple question.
*“I want to provide a list of all the children bach had. What would be a suitable google query”
It then responded with.
“To compile a comprehensive list of Johann Sebastian Bach’s children, a suitable Google query would be: “List of Johann Sebastian Bach’s children names”. This query is specific enough to indicate that you’re looking for a detailed list, including the names of all the children, which should yield targeted results.”
The following step I did manually, but is something you would normally have automated.
I put the suggested query in google, I quickly grabbed the first 5 links and then put the following in chatGPT.
The top 5 results in google are the pages I provided below. Browse to each page, and answer the query “List of Johann Sebastian Bach’s children names”. Just answer the query, but let me know if there is conflicting information on the page.
Johann Sebastian Bach had 20 children in total. With his first wife, Maria Barbara Bach, he had seven children, four of whom survived into adulthood: Catharina Dorothea, Wilhelm Friedemann, Carl Philipp Emanuel, and Johann Gottfried Bernhard. With his second wife, Anna Magdalena Wilcke, he had 13 children, of whom six survived into adulthood: Gottfried Heinrich, Elisabeth Juliane Friederica, Johanna Carolina, Regina Susanna, Johann Christoph Friedrich, and Johann Christian
Going over the search results myself seems to confirm this list. Most importantly, except for the initial input, all of this can be automated. And of course, a lot of it can be done better, as I didn’t want to spend too much time.
Literally the worst possible usage. They’re syntax generators, not search engines, and not knowledge fonts.
I don’t know how to say this in a less direct way. If this is your take then you probably should look to get slightly more informed about what LLMs can do. Specifically, what they can do if you combine them with with some code to fill the gaps.
Things LLMs can do quite well:
These are all the building blocks for searching on the internet. If you are talking about local documents and such retrieval augmented generation (RAG) can be pretty damn useful.
That’s not entirely fair either though… They can incorrectly summarize, omit important information, or just make stuff up.
Ask it to search or list all of Bach’s children and you can see the wheels completely fall off. It was inventing people with actual fake birth and death dates and also gave me some of Handel’s children!
What do you mean by “it”? The chatGPT interface? Could be, but then you are also missing the point I am making.
After all, chatGPT is just one of the possible implementations of LLMs and indeed not perfect in how they implemented some things like search. In fact, I do think that they shot themselves in the foot by implementing search through bing and implementing it poorly. It basically is nothing more than a proof of concept tech demo.
That doesn’t mean that LLM’s are useless for tasks like searching, it just means that you need to properly implement the functionality to make it possible. It certainly is possible to implement search functionality around LLMs that is both capable and can be reviewed by a human user to make sure it is not fucking up.
Let me demonstrate. I am doing some steps that you would normally automate with conventional code:
I started about by asking chatGPT a simple question.
It then responded with.
The following step I did manually, but is something you would normally have automated. I put the suggested query in google, I quickly grabbed the first 5 links and then put the following in chatGPT.
It then proceeded to give me the following answer
Going over the search results myself seems to confirm this list. Most importantly, except for the initial input, all of this can be automated. And of course, a lot of it can be done better, as I didn’t want to spend too much time.
Gpt is fantastic at search. Like, check its work but it’ll check hundreds of pages of results way faster than you can.