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

111–120 of 174 posts

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

#111

Post by msabalau »

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".

Pragmatically, the statement was made famous in English by a conservative US president, addressing the nation, including his supporters, who trusted him, but not the Soviets with whom he was negotiating.

Saying, in effect: "you trust in me, I'm choosing to trust that it makes sense to make agreement with the USSR, and we are going to verify it, just as we would with any serious business, as is proverbially commonsensical" is a perfectly intelligible.

There is nothing cunning about clinging to a single, superficial, context free reading of language.

Human speech and writting is not code, ambiguity and containing a range of possible meanings is part of its power and value.

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

#112

Post by stavros »

rpdillon wrote: post #103
stavros wrote: post #73

Earlier quoted context omitted.

We're getting into the definition of trust, but to me trust means exactly "I don't need to verify". If I say I trust you to write correct code, I don't mean "I'm sure your mistakes won't be intentional", I mean "I'm sure you won't have mistakes". If I need to check your code for mistakes, I don't trust you to write correct code. I don't know anyone who will hear "I trust you to write correct code, now let me make sur…

> to me trust means exactly "I don't need to verify". If you use the slightly weaker definition that trust means you have confidence in someone, then the adage makes sense.

The issue here is that the only value of the adage is in the sleight of hand it lets you perform. If someone asks "don't you trust me?" (ie "do you have to verify what I do/say?"), you can say "trust, but verify!", and kind of make it sound like you do trust them, but also you don't really.

The adage doesn't work under any definition of trust other than the one it's conflicting with itself about.

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

#113

Post by stavros »

Lerc wrote: post #92
cj wrote: post #75

Earlier quoted context omitted.

“I trust that you believe your code is correct, now let’s double check”. Or maybe the proverb needs to be rewritten as “feign trust and verify”

Or assume good faith but, since anyone can make mistakes, check the work anyway. That's a bit wordy but I'm sure someone can come up with a pithy phrase to encapsulate the idea.

"Trust, but verify"?

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

#114

Post by neom »

stavros wrote: post #109
IWeldMelons wrote: post #82

Earlier quoted context omitted.

This is not quite true. "Trust" is to give a permission for someone to act on achieving some result. "Verify" means assess the achieved result, and correct aposteriori the probability with which said person is able to achieve the abocementioned result. This is the way Bayesian reasoning works. Trust has degrees. What you have brought is "unconditional trust". Very rarely works.

> "Trust" is to give a permission for someone to act on achieving some result. This would make the sentence "I asked him to wash the dishes properly, but I don't trust him", as your definition expands this to "I asked him to wash the dishes properly, but I didn't give him permission to achieve this result". If you say "I asked someone to do X but I don't trust them", it means you aren't confident they'll do it proper…

Why could I not say "I trusted him to do the dishes properly, after he was done, I verified, it's a good thing I trusted him to do the dishes properly, my supervision would have been unwarranted and my trust was warranted?"

I trusted someone to do their task correctly, after the task was done, I verified my trust was warranted.

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

#115

Post by layer8 »

aussieguy1234 wrote: post #37

I used a screenshot of my internet banking transaction list with GPT4-o to get a list of transactions for my company tax return. Visually verified the results and they were correct. Earlier, a product manager sent me a list of company id's to turn on a feature flag for as a screenshot. Rather than enter them all in manually, I used that to get GPT4-o to generate a comma separated list from the screenshot. Again, work…

OpenAI must be happy to get all that confidential information. ;)

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

#116

Post by stavros »

msabalau wrote: post #111
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".

Pragmatically, the statement was made famous in English by a conservative US president, addressing the nation, including his supporters, who trusted him, but not the Soviets with whom he was negotiating. Saying, in effect: "you trust in me, I'm choosing to trust that it makes sense to make agreement with the USSR, and we are going to verify it, just as we would with any serious business, as is proverbially commonsens…

So "trust me, but verify others"? Where have you seen this adage used in this sense? It's not even used like that in the original Russian, where Reagan lifted it from.

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

#117

Post by websap »

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…

It would be interesting to see how well does a human do it? Are they correct more than 99.9% of the time?

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

#118

Post by millzlane »

This was my first use of ChatGPT maybe 1.0 I don't really remember but it was early last year sometime. I just started college for the first time and had a list of due dates for assignments.

I asked chatGPT "Can you make me an ics file from this list of dates"

It did it instantly and told me to save the file in a text editor as an .ics file. But it messed up and put the assignments and discuissions on the same week.

I ask "Do the same thing but move the discussion questions to the following tuesday, and put the assignment details in the details of the meeting.

It spit out a perfect .ics file.

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

#119

Post by hereme888 »

Months ago I did this with ChatGPT.

It was unable to create the .ics directly at first, but at least it wrote the python script that created the .ics.

I first ask the LLM to write out the calendar events in a markdown table to double-check it read everything correctly, and then create the file.

A different prompting strategy later on, ai think with example .ics formatting, resulted in a correct .ics. I just had to *emphasize* the time zone.

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

#120

Post by shade »

I did something similar recently with my daughter's school calendar and ChatGPT with gpt-4o; her school has a ton of closures/teacher work days, I fed the PDF of the calendar in and asked it for all the dates that impacted 2nd grade, then asked it to create an icalendar file for them.

Oddly, it didn't want to create the actual file, but gave me a Python script for doing so; you just need to be sure to tell it what time zone you are working in and that you want it to be an all-day event, or you'll get suboptimal results.

Post reply on HN