←back to thread

An LLM is a lossy encyclopedia

(simonwillison.net)
509 points tosh | 2 comments | | HN request time: 0s | source

(the referenced HN thread starts at https://news.ycombinator.com/item?id=45060519)
Show context
latexr ◴[] No.45101170[source]
A lossy encyclopaedia should be missing information and be obvious about it, not making it up without your knowledge and changing the answer every time.

When you have a lossy piece of media, such as a compressed sound or image file, you can always see the resemblance to the original and note the degradation as it happens. You never have a clear JPEG of a lamp, compress it, and get a clear image of the Milky Way, then reopen the image and get a clear image of a pile of dirt.

Furthermore, an encyclopaedia is something you can reference and learn from without a goal, it allows you to peruse information you have no concept of. Not so with LLMs, which you have to query to get an answer.

replies(10): >>45101190 #>>45101267 #>>45101510 #>>45101793 #>>45101924 #>>45102219 #>>45102694 #>>45104357 #>>45108609 #>>45112011 #
simonw ◴[] No.45101190[source]
I think you are missing the point of the analogy: a lossy encyclopedia is obviously a bad idea, because encyclopedias are meant to be reliable places to look up facts.
replies(5): >>45101249 #>>45101251 #>>45102590 #>>45105765 #>>45105785 #
checkyoursudo ◴[] No.45102590[source]
I am sympathetic to your analogy. I think it works well enough.

But it falls a bit short in that encyclopedias, lossy or not, shouldn't affirmatively contain false information. The way I would picture a lossy encyclopedia is that it can misdirect by omission, but it would not change A to ¬A.

Maybe a truthy-roulette enclyclopedia?

replies(1): >>45105295 #
1. tomrod ◴[] No.45105295[source]
I guarantee every encyclopedia has mistakes.
replies(1): >>45106166 #
2. Jensson ◴[] No.45106166[source]
I remember a study where they checked if wikipedia had more errors than paper encyclopedias, and they found there were about as many errors in both.

That study ended the "you can't trust wikipedia" argument, you can't trust anything but wikipedia is an as good as it gets second hand reference.