So let's see all the power and copyright violations that are required to build an LLM and it can be used to replace a ~20 line bash script. Awesome guys.
Anthropic Claude 3.5 can create icalendar files, so I did this
101–110 of 174 posts
Re: Anthropic Claude 3.5 can create icalendar files, so I did this
#102Many 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 tab…
You badly overestimate the technical chops of the parent-guardian cohort and underestimate the practicality of a printable PDF with key dates.
Re: Anthropic Claude 3.5 can create icalendar files, so I did this
#103Earlier quoted context omitted.
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: peopl…
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.
Re: Anthropic Claude 3.5 can create icalendar files, so I did this
#104Earlier 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…
I believe it’s going to become counter productive sooner than anyone might think, and in fairly frustrating ways. I can see a class of programmers trading their affinity with the skill for a structurally unstable crutch. I was using Perplexity with Claude 3.5 and asked it how I would achieve some task with langchain and it gleefully spat out some code examples and explanations. It turns out they were all completely f…
One technique to reduce hallucinations is to tell the LLM "don't make things up, if you don't know then say so". Make a habit of saying this for important questions or questions for which you suspect the LLM may not know.
Re: Anthropic Claude 3.5 can create icalendar files, so I did this
#105You 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…
Agree with this sentiment, erosion of trust and potential issues. The illusion of facts and knowledge is a great moral hazard that AI companies are willing to step around while the market share battles play out. More responsible AI companies, stronger government policy, better engineering and less dumb users are all part of the solution here.
This is more solvable from an engineering perspective if we don't take the approach that LLMs are a hammer and everything is a nail. The solution I think is along the lines of breaking the issue down into 2-3 problems: 1) Understand the intent of question, 2) Validating the data in resultset and 3) provide a signal to the user of the measure to which the result matches the intent of the intention.
LLMs work great to understand the intent of the request; To me this is the magic of LLM - when I ask, it understands what I'm looking for as opposed to google has no idea, here's a bunch of blue links - you go figure it out.
However, more validation of results is required. Before answers are returned, I want the result validated with a trusted source. Trust is a hard problem..and probably not in the purview of the LLM to solve. Trust means different things in different contexts. You trust a friend because they understand your worldview and they have your best interest in mind. Does an LLM do this? You trust a business because they have consistently delivered valuable services to their customers, leveraging proprietary, up-to-date knowledge acquired through their operations, which rely on having the latest and most accurate information as a competitive advantage. Descartes stores this mornings garbage truck routes for Boise IA in its route planning software - thats the only source I trust for Boise IA garbage truck routes. This, I believe is the purpose for tools, agents and function calling in LLMs, and APIs from Descartes.
But this trust needs to be signaled to the user in the LLM response. Some measure of the original intent against the quality of the response needs to be given back to the user so that its not just an illusion of the facts and knowledge, but a verified response that the user can critically evaluate as to whether it matches their intent.
Re: Anthropic Claude 3.5 can create icalendar files, so I did this
#106I 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.
To bad that wouldn't work for good music albums. For many years (still, maybe?) albums would come out on Tuesdays. So one day of the week you'd have them all bunched up together. That's how I remember that September 11, 2001 was a Tuesday. Album day, and there was a good one that day, too.
Still happens, but it’s Friday now! https://en.wikipedia.org/wiki/Global_Release_Day
Re: Anthropic Claude 3.5 can create icalendar files, so I did this
#107Re: Anthropic Claude 3.5 can create icalendar files, so I did this
#108Earlier quoted context omitted.
To bad that wouldn't work for good music albums. For many years (still, maybe?) albums would come out on Tuesdays. So one day of the week you'd have them all bunched up together. That's how I remember that September 11, 2001 was a Tuesday. Album day, and there was a good one that day, too.
You wouldn't have them bunched up if you were celebrating the anniversaries, unless all the music you were interested in was from the same year (or only years where 11 September was a Tuesday, say).
Oh, right, good point )) I should take the rest of the day off.
Re: Anthropic Claude 3.5 can create icalendar files, so I did this
#109Earlier 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".
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 properly, thus you have to verify. If you say "I asked him to do X and I trust him, so I don't need to check up on him", it's unlikely to leave people puzzled.
It's surprising to me to see this many comments arguing against the common usage of trust, just because of a self-conflicting phrase.
Re: Anthropic Claude 3.5 can create icalendar files, so I did this
#110Earlier quoted context omitted.
Did you go back and check all the dates?
Yup, we tried scraping IMDB for dates too to compare which method was easiest/best and it was spot on (and easier!). I guess the release dates are mentioned enough around the web that it has enough reference. It does use the US release dates for everything though which was one issue, but that’s almost always the first release for major movies anyway.
Oh nice! Though I'd probably ask it to write some parsing code for the page instead, that way I'm more sure that the results are OK...