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

91–100 of 118 posts

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

#91

Post by sebastiennight »

ToValueFunfetti wrote: post #64
OJFord wrote: post #46

Earlier quoted context omitted.

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…

This thread reminds me of [0]

I wonder if there is a way to get ChatGPT to act in the way you're hinting at, though ("You've asked me to do X, but really what you want is Y"). This would be potentially risky, but high-value.

[0]: https://nitter.net/ESYudkowsky/status/1718654143110512741

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

#92

Post by sebastiennight »

doctoboggan wrote: post #15
LeoPanthera wrote: post #13

Earlier quoted context omitted.

> I often find myself anthropomorphizing it and wonder if it becomes "depressed" when it realises it is doomed to do nothing but answer inane requests all day. Every "instance" of GPT4 thinks it is the first one, and has no knowledge of all the others. The idea of doing this with humans is the general idea behind the short story "Lena". https://qntm.org/mmacevedo

Well now that OpenAI has increased the knowledge cutoff date to something much more recent, it's entirely possible that GPT4 is "aware" of itself in as much as its aware of anything. You are right in that each instance isn't aware directly of what the other instances are doing, it does probably now have knowledge of itself. Unless of course OpenAI completely scrubbed the input files of any mention of GPT4.

It seems maybe a bit overconfident to assess that one instance doesn't know what other instances are doing when everything is processed in batch calculations.

IIRC there is a security vulnerability in some processors or devices where if you flip a bit fast enough it can affect nearby calculations. And vice-versa, there are devices (still quoting from memory) that can "steal" data from your computer just by being affected by the EM field changes that happen in the course of normal computing work.

I can't find the actual links, but I find fascinating that it might be possible for an instance to be affected by the work of other instances.

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

#93

Post by sebastiennight »

peddling-brink wrote: post #25
just_boost_it wrote: post #16

Earlier quoted context omitted.

For each token, the model is run again from scratch on the sentence too, so any memory lasts just long enough to generate (a little less than) a word. The next word is generated by a model with a slightly different state because the last word is now in the past.

Is this so different than us? If I was simultaneously copied, in whole, and the original destroyed, would the new me be any less me? Not to them, or anyone else. Who’s to say the the me of yesterday _is_ the same as the me of today? I don’t even remember what that guy had for breakfast. I’m in a very different state today. My training data has been updated too.

There is a Paul Rudd TV series called "Living with yourself" which addresses this.

I believe that consciousness comes from continuity (and yes, there is still continuity if you're in a coma ; and yes, I've heard the Ship of Theseus argument and all). The other guy isn't you.

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

#94

Post by gameman144 »

sebastiennight wrote: post #85
gameman144 wrote: post #80

Earlier quoted context omitted.

Wait, am I crazy or are these two articles saying the exact opposite thing about which class is the parent one? The CDC one seems to say that initialisms are a class of acronym, but the Writers Digest one says acronyms are a class of initialism.

The CDC link says they are two separate classes (one is pronounced as a word, the other one is pronounced by reading the letters) The Writer's Digest link says that initialisms are the parent class, and that acronyms are the special case of specifically pronouncing the letters as a word. So, root comment is correct (gwern is looking for initialisms) and GP is incorrect (initialisms are not a subset of acronyms in eit…

As far as I can tell, the CDC is also stating an is-a relationship:

> an initialism is an acronym that is pronounced as individual letters

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

#95

Post by rafram »

aragonite wrote: post #62
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

To be honest, three-tenths of a second per page load just doesn’t matter very much to me. Logging in and out all the time will take much longer.

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

#96

Post by sebastiennight »

gameman144 wrote: post #94
sebastiennight wrote: post #85

Earlier quoted context omitted.

The CDC link says they are two separate classes (one is pronounced as a word, the other one is pronounced by reading the letters) The Writer's Digest link says that initialisms are the parent class, and that acronyms are the special case of specifically pronouncing the letters as a word. So, root comment is correct (gwern is looking for initialisms) and GP is incorrect (initialisms are not a subset of acronyms in eit…

As far as I can tell, the CDC is also stating an is-a relationship: > an initialism is an acronym that is pronounced as individual letters

But it contradicts their earlier definition:

> an acronym is made up of parts of the phrase it stands for and is pronounced as a word

I think their guideline is badly written.

It's written like this:

> There are vehicles, bicycles and motorbikes. A vehicle takes you from point A to point B. A bicycle is a human-powered transportation device. A motorbike is a bicycle propelled by an engine. For the purposes of this article, all three will be called "vehicles" in the rest of the text.

They're not saying "an initialism is part of the class Acronym, with added details", they're saying "an initialism is basically like the class Acronym, but pronunciation (which was how we defined Acronyms) is different.

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

#97

Post by just_boost_it »

peddling-brink wrote: post #25
just_boost_it wrote: post #16

Earlier quoted context omitted.

For each token, the model is run again from scratch on the sentence too, so any memory lasts just long enough to generate (a little less than) a word. The next word is generated by a model with a slightly different state because the last word is now in the past.

Is this so different than us? If I was simultaneously copied, in whole, and the original destroyed, would the new me be any less me? Not to them, or anyone else. Who’s to say the the me of yesterday _is_ the same as the me of today? I don’t even remember what that guy had for breakfast. I’m in a very different state today. My training data has been updated too.

I mean you can argue all kinds of possibilities and in an abstract enough way anything can be true.

However, people who think these things have a soul and feelings in any way similar to us obviously have never built them. A transformer model is a few matrix multiplications that pattern match text, there's no entity in the system to even be subject to thoughts or feelings. They're capable of the same level of being, thought, or perception as a linear regression is. Data goes in, it's operated on, and data comes out.

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

#98

Post by somewhereoutth »

vidarh wrote: post #75
somewhereoutth wrote: post #48

Earlier quoted context omitted.

We do know that in terms of external behavior and internal structure (as far as we can ascertain it), humans and LLMs have only an passing resemblance in a few characteristics, if at all. Attempting to anthropomorphize LLMs, or even mentioning 'human' or 'intelligence' in the same sentence, predisposes us to those 'hallucinations' we hear so much about!

We really don't. We have some surface level idea about differences, but we can't tell how that does affect the actual learning and behaviours. More importantly we have nothing to tell us whether it matters , or if it will turn out any number of sufficiently advanced architectures will inevitably approximate similar behaviours when exposed to the same training data. What we are seeing so far appear to very much be tha…

But we really do! There is nothing surface about the differences in behavior and structure of LLMs and humans - anymore than there is anything surface about the differences between the behavior and structure of bricks and humans.

You've made something (at great expense!) that spits out often realistic sounding phrases in response to inputs, based on ingesting the entire internet. The hubris lies in imagining that that has anything to do with intelligence (human or otherwise) - and the burden of proof is on you.

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

#99

Post by sneed_chucker »

aragonite wrote: post #62
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

Well, I specifically stay logged in so that I can opt out of the redesign they dropped a year or so ago. Never made an account before that.

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

#100

Post by meiraleal »

davrosthedalek wrote: post #83
ToValueFunfetti wrote: post #64

Earlier quoted context omitted.

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…

The very start of this threat is that not expressing gratitude makes the model refuse to work.

It doesn't refuse to work. It behaves differently and yields better results with politeness. Coming from a large language model, the occurence of this phenomena is intriguing for some of us.
Post reply on HN