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

61–70 of 174 posts

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

#61

Post by surfingdino »

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…

Google's Gemini dev docs contain a few of such warnings. For a good reason, these models make stuff up and the domain where ROI is positive is small.

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

#63

Post by albert_e »

Many folks like schools, employers, etc still publish calendars in PDF format.

They spend more time on branding and visual formatting, than trying to create the same in formats that we can import into our calendar apps and actually use it practically.

I wonder if there is a two step process we can follow that will more robustly generalize ...

1. Read any document and convert into into a simple table that tries to tabulate: date, time (+timezone), venue, url, notes, recurrence

2. Read a table that roughly has the above structure and use that to create google/ical/ics files or links

We may be able to fine tune a model or agent separately to do each step very well.

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

#64

Post by Diti »

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".

French armed forces have a better version of this saying. “Trust does not exclude control.” They’re still going to check for explosives under cars that want to park in French embassies.

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

#65

Post by tmikaeld »

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 why I don't use code LLM code generators for citing or outputting a solution that includes the current code, because it's inclined to remove parts that it thinks don't matter, but rather matter a lot further down the line. And if it's not caught in code reviews, that can cause severe and difficult to debug issues. I'm sure there will be an epidemic of these issues in a few years, because developers are definitely lazy enough to rely on it.

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

#67

Post by dkga »

That’s a great step forward.

I use a combination of the Reminders and Calendar apps to mark entries of academic conferences I participate. One interesting thing for me personally would be to find a way to read the appointments in the Reminders app (presumably a sqlite3 db somewhere in iCloud) and create corresponding dates in the calendar, such that whenever I add a reminder to submit papers to a conference, this would automagically block that calendar slot for the dates of the conference such that I know not to schedule in person meetings with anyone in those dates.

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

#68

Post by franze »

> I tried the exact same thing in ChatGPT -- it identified the dates in the images, but it was unable to create an .ics file. However, it did give me some Python code to create the ics file for me.

well i constantly let ChatGPT create my calendar entries, either via Google Calendar links or ics files or QR codes.

Don't know what went wrong there.

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

#69

Post by victorbjorklund »

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…

yea, I seen it alot on social media where people use ChatGPT as a source for things it possible cant know. Often with leading questions.

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

#70

Post by cj »

stavros wrote: post #47
cromka wrote: post #44

Earlier quoted context omitted.

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

Yes, which boils down to "verify".

It's possible to trust (or have faith) in my car being able to drive another 50k miles without breaking down. But if I bring it to a mechanic to have the car inspected just in case, does that mean I never had trust/faith in the car to begin with?

"I trust my coworkers write good code, but I verify with code reviews" -- doing code reviews doesn't mean you don't trust your coworker.

Yet another way to look at it: people can say things they believe to be true but are actually false (which isn't lying). When that happens, you can successfully trust someone in the sense that they're not lying to you, but the absence of a lie doesn't guarantee a truth, so verifying what you trust to be true doesn't invalidate your trust.

Post reply on HN