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

71–80 of 81 posts

Re: ChatGPT as a Calculator for Words

#71

Post by rimliu »

dror wrote: post #21
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…

He can make the same criticism of Internet searches as he does of GPT: you shouldn't trust them until you validate them. I find that GPT's answers are for the most part more reliable the searches, specifically today's searches. In the last 12 months, search results have become so spammy with AI generated pages (oh the irony), that it's hard to find reliable answers. So like search, I look at GPT's answers with a grai…

I imagine ChatGPT will go from the "future changing" to "glorified spam generator" quite quickly.

Re: ChatGPT as a Calculator for Words

#72

Post by jazzyjackson »

akhilpotla wrote: post #47
dror wrote: post #21

Earlier quoted context omitted.

He can make the same criticism of Internet searches as he does of GPT: you shouldn't trust them until you validate them. I find that GPT's answers are for the most part more reliable the searches, specifically today's searches. In the last 12 months, search results have become so spammy with AI generated pages (oh the irony), that it's hard to find reliable answers. So like search, I look at GPT's answers with a grai…

Speaking of AI generated pages, I wonder how OpenAI filter these low quality web pages out of their training set as they continue to training. Also, I wonder how they decide what code is worth training on. Because a lot of code is written in poor style/has technical debt, it might be the case that these LLMs in the long run lead to an increase in the technical debt in our society. Plus, eventually, and this might alr…

yea i'm kind of shocked none of these models implement any kind of fingerprinting, something encoded in zero width spaces or other invisible unicode. It would be trivial to delete it but for the vast majority of cases, it would allow content to be flagged as model output-do not ingest

Re: ChatGPT as a Calculator for Words

#73

Post by layer8 »

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…

The internet allows you to corroborate alleged facts by looking at further sources, following references, etc. Or when you end up not finding anything useful that substantiates what you’re looking for, that can serve as a conclusion as well. You get a feeling for it after a while. ChatGPT by itself however can usually only serve as a starting point. It doesn’t allow you to reach the same level of confidence that a googling session can. I would say they complement each other. But if given the choice of only being allowed to use one of the two, I would opt for the search engine.

Re: ChatGPT as a Calculator for Words

#74

Post by pmoriarty »

dragonwriter wrote: post #41
pmoriarty wrote: post #38

Earlier quoted context omitted.

One thing I've been impressed by recently is ChatGPT's ability to explain epigrams. How can it explain them effectively if it's just a "stochastic parrot" or a "blurry jpeg"? Neither fits what it does. Don't such effective explanations require some sort of understanding? Below is an example explanation, and there are more here: [1] --- Explain "In software systems it is often the early bird that makes the worm." This…

It literally misses any explanation of the only thing that distinguishes the epigram from the proverb it refers to. While identifying, and reproducing, with simple contextual substitutions, and explanation of the proverb referenced is not a small feat compared to where this kind of technology was a few years ago, its pretty darned far from either (1) actually explaining the epigram, or (2) making the argument you try…

What is it missing? The explanation seems fine to me.

Anyway, I've run dozens of epigrams through it, almost none of which are based on any known proverbs, and it did great on almost all of them.

Even if you weren't impressed by this one, I encourage you to check out some of its other explanations at the link above.

Re: ChatGPT as a Calculator for Words

#75

Post by lupire »

akhilpotla wrote: post #47
dror wrote: post #21

Earlier quoted context omitted.

He can make the same criticism of Internet searches as he does of GPT: you shouldn't trust them until you validate them. I find that GPT's answers are for the most part more reliable the searches, specifically today's searches. In the last 12 months, search results have become so spammy with AI generated pages (oh the irony), that it's hard to find reliable answers. So like search, I look at GPT's answers with a grai…

Speaking of AI generated pages, I wonder how OpenAI filter these low quality web pages out of their training set as they continue to training. Also, I wonder how they decide what code is worth training on. Because a lot of code is written in poor style/has technical debt, it might be the case that these LLMs in the long run lead to an increase in the technical debt in our society. Plus, eventually, and this might alr…

If they aren't using Bing as a quality filter, they are crazy or stupid.

Re: ChatGPT as a Calculator for Words

#77

Post by lupire »

simonw wrote: post #23
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 tried to hint at that with "Using them as an alternative to a search engine such as Google is one of the most obvious applications—and for a lot of queries this works just fine." I agree: I do use it as a search engine myself for a bunch of things, but those tend to be things where I've developed a strong intuition that it's likely to give me a reasonable result. People who haven't developed that intuition yet tend…

How useful is it if you have to know what you expect the answer to be? How do you know you are right in your calls of when to trust it? This smells like a confirmation bias machine.

Re: ChatGPT as a Calculator for Words

#78

Post by anotherpaulg »

dror wrote: post #53
anotherpaulg wrote: post #45

Earlier quoted context omitted.

Gish looks really nice. I'm going to give it a try. It seems like you've been using similar workflows to what I've been trying for coding with gpt? https://github.com/paul-gauthier/easy-chat#created-by-chatgp...

Pretty much, except that I'm automating everything as much as I can, so that I just give the instructions and GPT does the rest. Here's an example: ----- #import ~/work/gish/tasks/coding.txt Change the following so that it looks for the open AI key in the following fashion: 1. env variable 2. os.home()/.openai 3. Throws an exception telling the user to put it in one of the above, and then exits #diff ~/work/gish/src/…

Ya, that's pretty much my workflow as well. Though for my little web app, I could give it the whole ball of html/css/js each time.

I haven't seen anyone else describing this workflow. Feed it the existing code, ask it to modify/improve/fix the code and output a new version of all the input code, review diffs.

It has downsides, because you can easily run out of context window of chatgpt-3.5-turbo. But I am getting much better code out of it versus other approaches I've tried. And it's a very efficient and natural workflow -- we're used to getting and reviewing diffs/PRs from human collaborators.

Re: ChatGPT as a Calculator for Words

#79

Post by simonw »

lupire wrote: post #77
simonw wrote: post #23

Earlier quoted context omitted.

I tried to hint at that with "Using them as an alternative to a search engine such as Google is one of the most obvious applications—and for a lot of queries this works just fine." I agree: I do use it as a search engine myself for a bunch of things, but those tend to be things where I've developed a strong intuition that it's likely to give me a reasonable result. People who haven't developed that intuition yet tend…

How useful is it if you have to know what you expect the answer to be? How do you know you are right in your calls of when to trust it? This smells like a confirmation bias machine.

It turns out to be absurdly useful, to a very un-intuitive degree.

One trick I use is to assume it has a "Wikipedia-level" knowledge of pretty much any topic. Often that's what I need! I want to ask some quick questions of someone eloquent who's read the Wikipedia article about something, to save me from having to read the whole thing myself.

If I need more expertise than you can get from reading Wikipedia I know that ChatGPT alone is very unlikely to cut it.

Re: ChatGPT as a Calculator for Words

#80

Post by tornato7 »

anotherpaulg wrote: post #45
dror wrote: post #21

Earlier quoted context omitted.

He can make the same criticism of Internet searches as he does of GPT: you shouldn't trust them until you validate them. I find that GPT's answers are for the most part more reliable the searches, specifically today's searches. In the last 12 months, search results have become so spammy with AI generated pages (oh the irony), that it's hard to find reliable answers. So like search, I look at GPT's answers with a grai…

Gish looks really nice. I'm going to give it a try. It seems like you've been using similar workflows to what I've been trying for coding with gpt? https://github.com/paul-gauthier/easy-chat#created-by-chatgp...

> The cost is based on the assumption that you're using GPT3.5 at $0.02 per 1000 tokens.

It's actually $0.002/1k, FYI

Post reply on HN