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

Anthropic Claude 3.5 can create icalendar files, so I did this

gregsramblings.com

Post reply on HN
Print view View original

41–50 of 174 posts

Re: Anthropic Claude 3.5 can create icalendar files, so I did this

#41

Post by Foobar8568 »

wenc wrote: post #3

You just have to double check the results whenever you tell Claude to extract lists and data. 99.9% of it will be correct, but sometimes 1 or 2 records are off. This kind of error is especially hard to notice because you're so impressed that Claude managed to do the extract task at all -- plus the results look wholly plausible upon eyeballing -- that you wouldn't expect anything to be wrong at all. But LLMs can get t…

Well for my case, I have 0 trust in chatgpt ( or local LLM) to extract properly data from a PDF file, especially if it's over a few pages.

Re: Anthropic Claude 3.5 can create icalendar files, so I did this

#42

Post by jillesvangurp »

I've been doing similar things with gpt 4o to simplify data entry. Right now, it's kind of useful to use but people are not systematically doing much yet with LLMs.

I think that's going to change because it's so obviously useful to do. Any work involving entering data into some form is something that can and will be automated now. Especially if you have the information in some printed or printable way. Just point your camera at the thing and quickly review the information.

Sucking up information that is out there on signs, posters, etc. can be amazingly useful. People put a lot of effort and money into communicating a lot of information visually that often does not exist in easily accessible digital form.

Re: Anthropic Claude 3.5 can create icalendar files, so I did this

#43

Post by stavros »

disillusioned wrote: post #25
wenc wrote: post #3

You just have to double check the results whenever you tell Claude to extract lists and data. 99.9% of it will be correct, but sometimes 1 or 2 records are off. This kind of error is especially hard to notice because you're so impressed that Claude managed to do the extract task at all -- plus the results look wholly plausible upon eyeballing -- that you wouldn't expect anything to be wrong at all. But LLMs can get t…

The "off by one" predilection of LLMs is going to lead to this massive erosion of trust in whatever "Truth" is supposed to be, and it's terrifying and going to make for a bumpy couple of years. (Or the complete collapse of objective knowledge, on a long enough time horizon.) It's one thing to ask an LLM when George Washington was born, and have it return "May 20, 2020." It's another thing to ask it, and have it matte…

This is semi-offtopic, but "trust but verify" is an oxymoron. Trusting something means I don't have to verify whether it's correct (I trust that it is), so the saying, in the end, is "don't verify but verify".

Re: Anthropic Claude 3.5 can create icalendar files, so I did this

#44

Post by cromka »

stavros wrote: post #43
disillusioned wrote: post #25

Earlier quoted context omitted.

The "off by one" predilection of LLMs is going to lead to this massive erosion of trust in whatever "Truth" is supposed to be, and it's terrifying and going to make for a bumpy couple of years. (Or the complete collapse of objective knowledge, on a long enough time horizon.) It's one thing to ask an LLM when George Washington was born, and have it return "May 20, 2020." It's another thing to ask it, and have it matte…

This is semi-offtopic, but "trust but verify" is an oxymoron. Trusting something means I don't have to verify whether it's correct (I trust that it is), so the saying, in the end, is "don't verify but verify".

A better phrase would be “Use it but verify”, simply.

Re: Anthropic Claude 3.5 can create icalendar files, so I did this

#47

Post by stavros »

cromka wrote: post #44
stavros wrote: post #43

Earlier quoted context omitted.

This is semi-offtopic, but "trust but verify" is an oxymoron. Trusting something means I don't have to verify whether it's correct (I trust that it is), so the saying, in the end, is "don't verify but verify".

A better phrase would be “Use it but verify”, simply.

Yes, which boils down to "verify".

Re: Anthropic Claude 3.5 can create icalendar files, so I did this

#48

Post by morsch »

disillusioned wrote: post #25
wenc wrote: post #3

You just have to double check the results whenever you tell Claude to extract lists and data. 99.9% of it will be correct, but sometimes 1 or 2 records are off. This kind of error is especially hard to notice because you're so impressed that Claude managed to do the extract task at all -- plus the results look wholly plausible upon eyeballing -- that you wouldn't expect anything to be wrong at all. But LLMs can get t…

The "off by one" predilection of LLMs is going to lead to this massive erosion of trust in whatever "Truth" is supposed to be, and it's terrifying and going to make for a bumpy couple of years. (Or the complete collapse of objective knowledge, on a long enough time horizon.) It's one thing to ask an LLM when George Washington was born, and have it return "May 20, 2020." It's another thing to ask it, and have it matte…

> why not just start there?

Because there are many categories of problems where it's much easier to verify a solution than it is to come up with it. This is true in computer science, but also more generally. Having an LLM restructure a document as a table means you have to proofread it, but it may be less tedious than doing it yourself.

I agree that asking straightforward factual questions isn't one of those cases much like I agree with most of your post.

Re: Anthropic Claude 3.5 can create icalendar files, so I did this

#49

Post by stavros »

sen wrote: post #19

I did a similar thing with ChatGPT-4o giving it a txt file list of movie names, and it returned the release date of each one, then gave me an iCal file of all those movies with their release dates as recurring yearly anniversary events so I can watch my favorite movies on their anniversary. I’ve done it for a few friends as well now and it’s got a 100% success rate so far, across over 100 total movie names.

Did you go back and check all the dates?

Re: Anthropic Claude 3.5 can create icalendar files, so I did this

#50

Post by ascorbic »

BoorishBears wrote: post #28
wenc wrote: post #18

Earlier quoted context omitted.

I pay for both Claude and ChatGPT. Claude 3.5 is now my daily driver but it still refuses to answer certain questions especially about geopolitics so I still have to go back to ChatGPT. I don’t agree that Claude is insanely superior to ChatGPT though. It still has trouble with LaTeX and optimization formulations. Its coding abilities are good but sometimes ChatGPT does better. This is why I keep both subscriptions. A…

I've never had 3.5 refuse a blunt callout, unlike 3 For example if I get a refusal to answer a question, a short blunt reply of "Are you seriously taking my question in such bad faith?" or "Why are you browbeating me for asking that" gets it unstuck

I like to use "Please interpret my request charitably", because charitability is one of the character traits that it is meant to be trained for. https://www.youtube.com/watch?v=iyJj9RxSsBY
Post reply on HN