Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

ChatGPT as a Calculator for Words

simonwillison.net

Post reply on HN
Print view View original

11–20 of 81 posts

Re: ChatGPT as a Calculator for Words

#11

Post by tbalsam »

skybrian wrote: post #9
ftxbro wrote: post #2

As a long time LLM enjoyer I just want to mention https://generative.ink/posts/simulators/ as I think it's by far the most insightful take on the GPT LLMs even though it was from before ChatGPT. It's better than blurry jpeg and stochastic parrot etc.

I think that article is misleading, because a simulator has rules. An LLM is better thought of as a storyteller, because at best it's going to follow whatever implicit rules there are very loosely and let you make rule changes of your own, more like Calvinball. Also, whatever loose rules it has are more literary than mathematical. Plot twists often work.

I find this to be a better explanation than "it's just regurgitating strings of text"

No, it is clearly not, and that is a very easily testable hypothesis.

Thank you for sharing.

Re: ChatGPT as a Calculator for Words

#12

Post by LelouBil »

tbalsam wrote: post #10

I've seen this take a lot, and I find it frustrating as it flies in the face of the information theory underpinning how large neural networks learn information. This is more than just a fancy zip file of Markov sequences. Someone has got to put a stop to this silly line of reasoning, I'm not sure why more people familiar with the math of deep learning aren't doing their best to dispel this particular belief (which pe…

Can you explain more ?

I know the basics of deep learning and I found the article accurate.

Re: ChatGPT as a Calculator for Words

#13

Post by stavros »

SomewhatLikely wrote: post #6

The author does a good job of pointing out what may be the strongest skills of LLMs but the claim they aren't useful as a search engine didn't ring particularly true. For many questions I have ChatGPT is the best tool to use because I know the topics I'm asking about are mentioned hundreds of times in the web, and the LLM can distill down at knowledge to the specifics I'm asking about. If you treat it as a friend who…

I'm convinced LLMs are amazing for search, because they're the only thing that managed to give me an answer when I was looking for some software I didn't know the general category name for. I described what I wanted the software to do, corrected its understanding with a few followup messages, and it gave me a list of alternatives that are exactly what I wanted, along with a category name.

Google, in comparison, returned absolutely irrelevant SEO spam.

Re: ChatGPT as a Calculator for Words

#14

Post by trc001 »

LelouBil wrote: post #12
tbalsam wrote: post #10

I've seen this take a lot, and I find it frustrating as it flies in the face of the information theory underpinning how large neural networks learn information. This is more than just a fancy zip file of Markov sequences. Someone has got to put a stop to this silly line of reasoning, I'm not sure why more people familiar with the math of deep learning aren't doing their best to dispel this particular belief (which pe…

Can you explain more ? I know the basics of deep learning and I found the article accurate.

I think parent is getting at the idea that dnn learns abstract representations of the data in whatever way is useful for the mode objective function. But I agree, the article still seems to present a reasonable argument

Re: ChatGPT as a Calculator for Words

#15

Post by sebzim4500 »

booleandilemma wrote: post #3

It makes me sad that the next time I enjoy a piece of writing, I'm going to have to wonder if it was "enhanced" or even written wholesale by ChatGPT. I don't feel the same with arithmetic at all.

When you read a novel, do you spend time worrying about what sections are 'as written' from the author and which sections were cleaned up by an editor?

Re: ChatGPT as a Calculator for Words

#16

Post by trc001 »

Good to see more people pointing out the problems using standalone llm (I.e. not connected to an external data source/the internet) for search. So many people I talk to dismiss gpt because it can’t answer some subject-specific question accurately.

Re: ChatGPT as a Calculator for Words

#17

Post by booleandilemma »

majormajor wrote: post #7
booleandilemma wrote: post #3

It makes me sad that the next time I enjoy a piece of writing, I'm going to have to wonder if it was "enhanced" or even written wholesale by ChatGPT. I don't feel the same with arithmetic at all.

Is this a result of the machine-instead-of-human-reviewer/editor difference, or because of a sense that the writing is less a "pure" output of a singular author?

Well I think it's like, you come to enjoy an author's particular style of writing, and if people are just going to use ChatGPT to write things for them, then they're not going to develop any style. Everyone might even end up all sounding the same.

With a calculator this is a feature. We want computations to be the same after all. Everyone should be able to get the same results when they enter the same numbers in. But this homogeneity doesn't belong in writing.

Re: ChatGPT as a Calculator for Words

#18

Post by happyzombies »

SomewhatLikely wrote: post #6

The author does a good job of pointing out what may be the strongest skills of LLMs but the claim they aren't useful as a search engine didn't ring particularly true. For many questions I have ChatGPT is the best tool to use because I know the topics I'm asking about are mentioned hundreds of times in the web, and the LLM can distill down at knowledge to the specifics I'm asking about. If you treat it as a friend who…

This is true about the search engine, and besides things you usually google aren’t guaranteed to be 100% accurate anyways. So how is using ChatGPT any different?

Sure things in Wikipedia or official documents could be accurate, but the internet is still full of misinformation

Re: ChatGPT as a Calculator for Words

#20

Post by ftxbro »

skybrian wrote: post #9
ftxbro wrote: post #2

As a long time LLM enjoyer I just want to mention https://generative.ink/posts/simulators/ as I think it's by far the most insightful take on the GPT LLMs even though it was from before ChatGPT. It's better than blurry jpeg and stochastic parrot etc.

I think that article is misleading, because a simulator has rules. An LLM is better thought of as a storyteller, because at best it's going to follow whatever implicit rules there are very loosely and let you make rule changes of your own, more like Calvinball. Also, whatever loose rules it has are more literary than mathematical. Plot twists often work.

The essay is long and complicated so I'm not sure how much of it you read closely, but it specifically addresses this distinction between the simulator and the simulacrum.

In the analogy of the essay, your argument would be like saying that reality cannot be simply the application of quantum physics, because you are allowed to make new rules like Calvinball within reality which are different from the rules of quantum physics.

Post reply on HN