Information Retrieval Quotes

Think of ChatGPT as a blurry JPEG of all the text on the Web. It retains much of the information on the Web, in the same way that a JPEG retains much of the information of a higher-resolution image, but, if you’re looking for an exact sequence of bits, you won’t find it; all you will ever get is an approximation. But, because the approximation is presented in the form of grammatical text, which ChatGPT excels at creating, it’s usually acceptable. You’re still looking at a blurry JPEG, but the blurriness occurs in a way that doesn’t make the picture as a whole look less sharp.

Doing research on the Web is like using a library assembled piecemeal by pack rats and vandalized nightly.

My mind is a chest of drawers. When I wish to deal with a subject, I shut all the drawers but the one in which the subject is to be found. When I am wearied, I shut all the drawers and go to sleep.

Where is the knowledge we have lost in information?

We need less memorization - I never memorized the periodic table of the elements - I've never used it, and I'm a physicist! I can look it up.

Facebook and Twitter have a ton of information they're trying to make sense of.

But every time our ability to access information and to communicate it to others is improved, in some sense we have achieved an increase over natural intelligence.

A capacity, and taste, for reading gives access to whatever has already been discovered by others.

People's minds are overloaded with information.

The problem in the 19th century with information was that we lived in a culture of information scarcity, and so humanity addressed that problem beginning with photography and telegraphy and the - in the 1840s. We tried to solve the problem of overcoming the limitations of space, time, and form.

When I need names they drop out of my head; when I don't need them they drop back.

The man who acquires an encyclopedia does not thereby acquire every line, every paragraph, every page, and every illustration; he acquires the possibility of becoming familiar with one and another of those things.

if it's not in my email archive, I don't know it

I don't like to read nonfiction. To me, fact is something I can look up.

But it seemed to me that as soon as you have computer storage you could put every point you wanted in - make the ones that are less relevant to your central topic, further away or allow the central topic to move as the reader proceeded.

Like some helpful person (hi, Mom) has tried to "'clean'" it, and suddenly you can't find anything?

Randomness works well in search sometimes better than humans.

I am learning to get online myself, and I will have that down fairly soon, getting on myself. I don’t expect to be a great communicator, I don’t expect to set up my own blog, but I am becoming computer literate to the point where I can get the information that I need.

Searching and learning is where the miracle process all begins.

Why don't I talk about Big Data? Because I am focused on intelligent answers and not speeds and feeds. It doesn't matter if it is quick if it's the wrong answer.

It's amazing what's buried in old, poorly digitized PDFs hosted on some random professor's website.

It's not like I'm an Internet geek or anything - I'm of an age where the Internet is not the first thing I think of when I need to find something out.

The Internet has got great tools. How we lived without Google all those years I don't know.

All knowledge is valuable to a librarian.

Before Google, I spent the summer building a program that would look at what websites you would go to and what websites other people would go to - and built a collaborative filtering program that helped you find related sites to look at.