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

Writing a GPT-4 script to check Wikipedia for the first unused acronym

gwern.net

Post reply on HN
Print view View original

61–70 of 118 posts

Re: Writing a GPT-4 script to check Wikipedia for the first unused acronym

#61

Post by mjburgess »

mlrtime wrote: post #57
DavidSJ wrote: post #20

I note that while E is more common than A if we're counting letters appearing anywhere in a word, A is substantially more common than E if we only count first letters of words: $ egrep -o . /usr/share/dict/words | tr a-z A-Z | sort | uniq -c | sort -rn 235415 E 201093 I 199606 A 170740 O 161024 R 158783 N 152868 T 139578 S 130507 L 103460 C 87390 U 78180 P 70725 M 68217 D 64377 H 51683 Y 47109 G 40450 B 24174 F 20181…

A bit off-topic, but this used to be (one of) my favorite unix admin interview questions. Given a file in linux, tell me the unique values of column 2, sorted by number of occurencies with the count. If the candidate knew 'sort | uniq -c | sort -rn' it was a medium-strong hire signal. For candidates that didn't know that line of arguments, I'd allow them to solve it anyway they wanted, but they couldn't skip it. The…

My intuitions start with: cut, wc, sort, uniq

Re: Writing a GPT-4 script to check Wikipedia for the first unused acronym

#62

Post by aragonite »

marginalia_nu wrote: post #32

I'll argue any civilized programmer should have a Wikipedia dump downloaded onto their machine. They're surprisingly small, and it saves you from having to use slow and unreliable APIs to do these types of basic processing tasks. They also let you do less basic processing tasks that would have been too expensive to expose over API.

Relatedly: to drastically improve Wikipedia loading speed for personal browsing purposes, do not stay logged in to your Wikipedia account. The reason as explained here (see top reply by baowolff)

https://news.ycombinator.com/item?id=36114477

Re: Writing a GPT-4 script to check Wikipedia for the first unused acronym

#63

Post by hiAndrewQuinn »

marginalia_nu wrote: post #32

I'll argue any civilized programmer should have a Wikipedia dump downloaded onto their machine. They're surprisingly small, and it saves you from having to use slow and unreliable APIs to do these types of basic processing tasks. They also let you do less basic processing tasks that would have been too expensive to expose over API.

1. Download http://static.wiki/.

2. Run it locally on https://datasette.io/.

3. ???

4. Profit?

Re: Writing a GPT-4 script to check Wikipedia for the first unused acronym

#64

Post by ToValueFunfetti »

OJFord wrote: post #46
meiraleal wrote: post #34

Earlier quoted context omitted.

> Having to be unconditionally nice to computers is extremely creepy in part because it conditions us to be submissive It's not a healthy mindset to relate politeness to submissiveness. although both behaviors might look similar from afar they are totally different

I think GP means being polite to something because otherwise it refuses to function is submissive, not that politeness is inherently. I might prefer my manager to ask me to do something politely, but it's still my job if he asks me rudely.

But the AI doesn't refuse to work unless you're polite. If my manager is polite with me, I'll have more morale and work a little harder. I'll also be more inclined to look out for my manager's interests- "You've asked me to do X, but really what you want is Y" vs. "Fine, you told me to do X, I'll do X". I don't think my manager is submitting to me when they're polite and get better results; I'm still the one who does things when I'm told.

Re: Writing a GPT-4 script to check Wikipedia for the first unused acronym

#65

Post by cypherpunks01 »

dojitza1 wrote: post #43

An interesting solution to the blind spot error (taken directly from Jeremy Howard's amazing guide to language models - https://www.youtube.com/watch?v=jkrNMKz9pWU ) is to erase the chat history and try again. Once GPT has made an error (or as the author of this article says, the early layers have irreversibly pruned some important data), it will very often start to be even more wrong.

When this happens, I'll usually say something along the lines of:

"This isn't working and I'd like to start this again with a new ChatGPT conversation. Can you suggest a new improved prompt to complete this task, that takes into account everything we've learned so far?"

It has given me good prompt suggestions that can immediately get a script working on the first try, after a frustrating series of blind spot bugs.

Re: Writing a GPT-4 script to check Wikipedia for the first unused acronym

#66

Post by nonethewiser »

mlrtime wrote: post #57
DavidSJ wrote: post #20

I note that while E is more common than A if we're counting letters appearing anywhere in a word, A is substantially more common than E if we only count first letters of words: $ egrep -o . /usr/share/dict/words | tr a-z A-Z | sort | uniq -c | sort -rn 235415 E 201093 I 199606 A 170740 O 161024 R 158783 N 152868 T 139578 S 130507 L 103460 C 87390 U 78180 P 70725 M 68217 D 64377 H 51683 Y 47109 G 40450 B 24174 F 20181…

A bit off-topic, but this used to be (one of) my favorite unix admin interview questions. Given a file in linux, tell me the unique values of column 2, sorted by number of occurencies with the count. If the candidate knew 'sort | uniq -c | sort -rn' it was a medium-strong hire signal. For candidates that didn't know that line of arguments, I'd allow them to solve it anyway they wanted, but they couldn't skip it. The…

> The candidates who copied the data in excel, usually didn't make it far.

Were they able to google? If not then excel makes perfect sense because the constraints are contrived.

Re: Writing a GPT-4 script to check Wikipedia for the first unused acronym

#67

Post by zamadatix »

vidarh wrote: post #33
zamadatix wrote: post #21

Earlier quoted context omitted.

It's not really trained to think like a person. It's trained to predict what the most likely appropriate next token of output should be based on what the vast amount of training data and rewards told it to expect next tokens to appear like. Said data already included conversations from emotion laden humans where starting with "Screw you, tell me how to do this math problem loser" is much less likely to result in a re…

We don't know what "think like a person" entails, so we don't know how different human thought processes are to predicting what goes next, and whether those differences are meaningful when making a comparison. Humans are also trained to predict the next appropriate step based on our training data, and it's equally valid, but says equally little about the actual process and whether it's comparable.

You don't need to understand much of what "move like a person" entails to understand it's not the same method as "move like a car" even though both start with energy and end with transportation. I.e. "we also predict the next appropriate step" isn't the same thing as "we go about predicting the next step in a similar way". Even without having a deep understanding of human consciousness what we do know doesn't line up with how LLMs work.

Re: Writing a GPT-4 script to check Wikipedia for the first unused acronym

#69

Post by marginalia_nu »

hiAndrewQuinn wrote: post #63
marginalia_nu wrote: post #32

I'll argue any civilized programmer should have a Wikipedia dump downloaded onto their machine. They're surprisingly small, and it saves you from having to use slow and unreliable APIs to do these types of basic processing tasks. They also let you do less basic processing tasks that would have been too expensive to expose over API.

1. Download http://static.wiki/ . 2. Run it locally on https://datasette.io/ . 3. ??? 4. Profit?

I built my own at encyclopedia.marginalia.nu, but basically, yes.

Re: Writing a GPT-4 script to check Wikipedia for the first unused acronym

#70

Post by vidarh »

zamadatix wrote: post #67
vidarh wrote: post #33

Earlier quoted context omitted.

We don't know what "think like a person" entails, so we don't know how different human thought processes are to predicting what goes next, and whether those differences are meaningful when making a comparison. Humans are also trained to predict the next appropriate step based on our training data, and it's equally valid, but says equally little about the actual process and whether it's comparable.

You don't need to understand much of what "move like a person" entails to understand it's not the same method as "move like a car" even though both start with energy and end with transportation. I.e. "we also predict the next appropriate step" isn't the same thing as "we go about predicting the next step in a similar way". Even without having a deep understanding of human consciousness what we do know doesn't line up…

What we do know is superficial at best, and tells us pretty much nothing relevant. And while there likely are structural differences (it'd be too amazing if the transformer architecture just chanced on the same approach), we're left to guess how those differences manifest and whether or not these differences are meaningful in terms of comparing us.

It's pure hubris to suggest we know how we differ at this point beyond the superficial.

Post reply on HN