A LLM is essentially the world information packed into a very compact format. It is the modern equivalent of the Library of Alexandria.
Claiming that your own knowledge is better than all the compressed consensus of the books of the universe, is very optimistic.
If you are not sure about the result given by a LLM, it is your task as a human to cross-verify the information. The exact same way that information in books is not 100% accurate, and that Google results are not always telling the truth.
>LLM is essentially the world information packed into a very compact format.
No, it's world information distilled to various parts and details that training deemed important. Do not pretend for one second that it's not an incredibly lossy compression method, which is why LLMs hallucinate constantly.
This is why training is only useful for teaching the LLM how to string words together to convey hard data. That hard data should always be retrieved via RAG with an independent model/code verifying that the contents of the response are correct as per the hard data. Even 4o hallucinates constantly if it doesn't do a web search and sometimes even when it does.
Well let's not forget that it's an opinionated source. There is also the point that if you ask it about a topic it will (often) give you the answer that has the most content about it (or easiest to access information).
I find that, for many, LLMs are addictive, a magnet, because it offers to do your work for you, or so it appears. Resisting this temptation is impossibly hard for children for example, and many adults succumb.
A good way to maintain a healthy dose of skepticism about its output and keep on checking this output, is asking the LLM about something that happened after the training cut off.
For example, I asked if lidar could damage phone lenses. And the LLM very convincingly argued it was highly improbable. Because that recently made the news as a danger for phone lenses, and wasn’t part of the training data.
This helps me stay sane and resist the temptation of just accepting LLM output =)
On a side note, the kagi assistant is nice for kids I feel because it links to its sources.
It’s eerie. It’s historical. These threads from these past two years about what the future of AI will be will read like ghost stories. Like Rose having flash backs of the Titanic. It’s worth documenting. We honestly could be having the most ominous discussion of what’s to come.
We sit around and complain about dips in hiring, that’s nothing. The iceberg just hit. We’ve got 6 hours left.
Yesterday I asked Chat GPT which was the Japanese Twin City for Venice (Italy).
This was just a quick offhand question because I needed the answer for a post on IG, so not exactly a death or life situation.
Answer: Kagoshima.
It also added that the "twin status" was officially set in 1965, and that Kagoshima was the starting point for the Jesuit Missionary Alessandro Valignano in his attempt to proselitize Japanese people (to Catholicism, and also about European Culture).
I never heard of Kagoshima, so I googled for it. And discovered it is the twin city of Neaples :/
So I then googled for "Venice Japanese Twin City" and got: Hiroshima.
I doublechecked this then I went back to ChatGPT and wrote:
"Kagoshima is the Twin City for Neaples.".
This triggered a websearch and finally it wrote back:
"You are right, Kagoshima is Twin City of Neaples since 1960."
Then it added "Regarding Venice instead, the twin city is Hiroshima, since 2023".
So yeah, a Library of Alexandria that you can count on as long as you have another couple of libraries to doublechek whatever you get from it.
Note also that this was very straightforward question, there is nothing to "analyze" or "interpret" or "reason about".
And yet the answer was completely wrong, the first date was incorrect even for Neaples (actually the ceremony was in May 1960) and the extra bits about Alessandro Valignano are not reported anywhere else: Valignano was indeed a Jesuit and he visited Japan multiple times, but Kagoshima is never mentioned when you google for him or if you check his wikipedia page.
You may understand how I remain quite skeptical for any application which I consider "more important than an IG title".
> Venice, Italy does not appear to have a Japanese twin city or sister city. While several Japanese cities have earned the nickname "Venice of Japan" for their canal systems or waterfront architecture, there is no formal sister city relationship between Venice and any Japanese city that I could find in the available information
If I want facts that I would expect the top 10 Google results to have, I turn search on. If I want a broader view of a well known area, I turn it off. Sometimes I do both and compare. I don’t rely on model training memory for facts that the internet wouldn’t have a lot of material for.
40 for quick. 40 plus search for facts. O4-mini high plus search for “mini deep research”, where it’ll hit more pages, structure and summarise.
And I still check the facts and sources to be honest. But it’s not valueless. I’ve searched an area for a year and then had deep research find things I haven’t.
It's a compressed statistical representation of text patterns, so it is absolutely true. You lose information during the process, but the quality is similar to the source data. Sometimes even above, as there is consensus when information is repeated across multiple sources.
10 month old account talking like that to the village elder
In fairness, the article is a lot more condescending and insulting to its readers than the comment you're replying to.
A LLM is essentially the world information packed into a very compact format. It is the modern equivalent of the Library of Alexandria.
Claiming that your own knowledge is better than all the compressed consensus of the books of the universe, is very optimistic.
If you are not sure about the result given by a LLM, it is your task as a human to cross-verify the information. The exact same way that information in books is not 100% accurate, and that Google results are not always telling the truth.
>LLM is essentially the world information packed into a very compact format.
No, it's world information distilled to various parts and details that training deemed important. Do not pretend for one second that it's not an incredibly lossy compression method, which is why LLMs hallucinate constantly.
This is why training is only useful for teaching the LLM how to string words together to convey hard data. That hard data should always be retrieved via RAG with an independent model/code verifying that the contents of the response are correct as per the hard data. Even 4o hallucinates constantly if it doesn't do a web search and sometimes even when it does.
Well let's not forget that it's an opinionated source. There is also the point that if you ask it about a topic it will (often) give you the answer that has the most content about it (or easiest to access information).
Agree.
I find that, for many, LLMs are addictive, a magnet, because it offers to do your work for you, or so it appears. Resisting this temptation is impossibly hard for children for example, and many adults succumb.
A good way to maintain a healthy dose of skepticism about its output and keep on checking this output, is asking the LLM about something that happened after the training cut off.
For example, I asked if lidar could damage phone lenses. And the LLM very convincingly argued it was highly improbable. Because that recently made the news as a danger for phone lenses, and wasn’t part of the training data.
This helps me stay sane and resist the temptation of just accepting LLM output =)
On a side note, the kagi assistant is nice for kids I feel because it links to its sources.
7 replies →
This is pre-Covid HN thread on work from home:
https://news.ycombinator.com/item?id=22221507
It’s eerie. It’s historical. These threads from these past two years about what the future of AI will be will read like ghost stories. Like Rose having flash backs of the Titanic. It’s worth documenting. We honestly could be having the most ominous discussion of what’s to come.
We sit around and complain about dips in hiring, that’s nothing. The iceberg just hit. We’ve got 6 hours left.
> We sit around and complain about dips in hiring, that’s nothing. The iceberg just hit. We’ve got 6 hours left.
At least we've got hacker news to ourselves, have we not ... https://news.ycombinator.com/item?id=44130743
Partially OT:
Yesterday I asked Chat GPT which was the Japanese Twin City for Venice (Italy). This was just a quick offhand question because I needed the answer for a post on IG, so not exactly a death or life situation.
Answer: Kagoshima. It also added that the "twin status" was officially set in 1965, and that Kagoshima was the starting point for the Jesuit Missionary Alessandro Valignano in his attempt to proselitize Japanese people (to Catholicism, and also about European Culture).
I never heard of Kagoshima, so I googled for it. And discovered it is the twin city of Neaples :/
So I then googled for "Venice Japanese Twin City" and got: Hiroshima. I doublechecked this then I went back to ChatGPT and wrote:
"Kagoshima is the Twin City for Neaples.".
This triggered a websearch and finally it wrote back:
"You are right, Kagoshima is Twin City of Neaples since 1960."
Then it added "Regarding Venice instead, the twin city is Hiroshima, since 2023".
So yeah, a Library of Alexandria that you can count on as long as you have another couple of libraries to doublechek whatever you get from it. Note also that this was very straightforward question, there is nothing to "analyze" or "interpret" or "reason about". And yet the answer was completely wrong, the first date was incorrect even for Neaples (actually the ceremony was in May 1960) and the extra bits about Alessandro Valignano are not reported anywhere else: Valignano was indeed a Jesuit and he visited Japan multiple times, but Kagoshima is never mentioned when you google for him or if you check his wikipedia page.
You may understand how I remain quite skeptical for any application which I consider "more important than an IG title".
Claude 4 Opus:
> Venice, Italy does not appear to have a Japanese twin city or sister city. While several Japanese cities have earned the nickname "Venice of Japan" for their canal systems or waterfront architecture, there is no formal sister city relationship between Venice and any Japanese city that I could find in the available information
I think GPT-4o got it wrong in your case because it searched Bing, and then read only fragments of the page ( https://en.wikipedia.org/wiki/List_of_twin_towns_and_sister_... ) to save costs for processing "large" context
1 reply →
If I want facts that I would expect the top 10 Google results to have, I turn search on. If I want a broader view of a well known area, I turn it off. Sometimes I do both and compare. I don’t rely on model training memory for facts that the internet wouldn’t have a lot of material for.
40 for quick. 40 plus search for facts. O4-mini high plus search for “mini deep research”, where it’ll hit more pages, structure and summarise.
And I still check the facts and sources to be honest. But it’s not valueless. I’ve searched an area for a year and then had deep research find things I haven’t.
o3 totally nailed it first shot. Hiroshima since 2023. Provides authoritative source (Venetian city press release): https://chatgpt.com/share/683f638a-3ce0-8005-91d6-3eb1df9f19...
What model?
People often say "I asked ChatGPT something and it was wrong", and then you ask them the model and they say "huh?"
The default model is 4.1o-mini, which is much worse than 4.1o and much much worse than o3 at many tasks.
4 replies →
No, don't think libraries, think "the Internet."
The Internet thinks all kinds of things that are not true.
Just like books then, except the internet can be updated
1 reply →
Even if this were true (it is not; that’s not how LLMs work), well, there was a lot of complete nonsense in the Library of Alexandria.
It's a compressed statistical representation of text patterns, so it is absolutely true. You lose information during the process, but the quality is similar to the source data. Sometimes even above, as there is consensus when information is repeated across multiple sources.
1 reply →