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

Teaching ChatGPT to speak my son’s invented language

szopa.medium.com

Post reply on HN
Print view View original

91–100 of 212 posts

Re: Teaching ChatGPT to speak my son’s invented language

#91

Post by xwdv »

joshribakoff wrote: post #85
jacobsenscott wrote: post #81

Earlier quoted context omitted.

Chat gpt can't do these things because it doesn't know it is doing anything with a goal. It doesn't know it is playing a game for example. It doesn't know what a game is.

The counter argument is if you just ask it, it will readily explain what a game is. How do we know you (as a human) actually know what a game is? I would have to test your knowledge and/or take your word for it.

That is not a counter argument. GPT creates the illusion of something that knows things, it doesn’t actually know anything.

It turns out if you had a super power where you always knew how to pick the next best word for a sentence, you could convince a lot of people you know stuff.

Is knowledge nothing more than a series of words in correct order?

Re: Teaching ChatGPT to speak my son’s invented language

#92

Post by School-Cotton »

wizzwizz4 wrote: post #82
anon84873628 wrote: post #35

>All of these differences can make it surprising and challenging for someone with an Indo-European language background to learn and use Kłeti. Ironically, Proto-Indo-European is believed to be far more complex than its modern descendants, as described by Wikipedia: >PIE is believed to have had an elaborate system of morphology that included inflectional suffixes (analogous to English child, child's, children, childre…

> as well as ablaut (vowel alterations, as preserved in English sing, sang, sung, song) Interestingly, English is gaining instances of ablaut. For example, dived seems to be being replaced by dove.

Woah, I didn’t even realize dove was etymologically unjustifiable[0]. I speak a variety of American English that’s almost indistinguishable from the educated standard, and it wouldn’t even have occurred to me that “dived” could be used as the past participle of “dive”.

Apparently “dove” is mostly common in North America.

[0] not “wrong”, since language is arbitrary so it’s meaningless to claim that any naturally occurring colloquial dialect is more correct than any other. But “etymologically unjustifiable” is still a meaningful concept.

Re: Teaching ChatGPT to speak my son’s invented language

#93

Post by ratg13 »

roflyear wrote: post #83
jacobsenscott wrote: post #81

Earlier quoted context omitted.

Chat gpt can't do these things because it doesn't know it is doing anything with a goal. It doesn't know it is playing a game for example. It doesn't know what a game is.

Correct. How do so many people get this wrong?

Movies, comics, books, sci-fi

Everyone has been primed to accept AI as an intelligent companion, not a talking search engine.

Re: Teaching ChatGPT to speak my son’s invented language

#94

Post by joshribakoff »

z3c0 wrote: post #89
joshribakoff wrote: post #85

Earlier quoted context omitted.

The counter argument is if you just ask it, it will readily explain what a game is. How do we know you (as a human) actually know what a game is? I would have to test your knowledge and/or take your word for it.

Being able to discern its word soup as a description of what constitutes a game is more a demonstration of you understanding what a game is, not it. And therein lies the magic of ChatGPT: it knows nothing, but the projected significance of the token arrangements it creates tugs on what we know, and that causes a profound feeling akin to interacting with something intelligent.

Lets rephrase this differently, no one can prove whether it “understands” or not, and the same for humans. No one can prove whether consciousness is an “illusion” for humans. Your brain might just use embeddings, too.

If you ask an average person if children understand what a game is, “yes” would be a common answer, but just like an AI model it may not have enough focus to play the game properly.

I believe this is the whole point behind “the turing test”.

If you instead argued it can’t experience emotion, i would agree.

Re: Teaching ChatGPT to speak my son’s invented language

#96

Post by dTal »

joshribakoff wrote: post #78
Buttons840 wrote: post #58

Earlier quoted context omitted.

Being able to learn within context, without updating weights is amazing. Imagine how much more efficient and/or powerful it could be if we found a way to update the weights in real time.

Maybe even more powerful would be reducing the number of examples needed to learn, eg less than one shot https://www.technologyreview.com/2020/10/16/1010566/ai-machi... updating weights in real time is useless if each update basically does nothing because it takes an insurmountable amount of training, on the other hand if i can give my model a succinct “lesson” i’d then be very willing to wait a while for it to “proc…

As I understand, that's basically what fine-tuning is?

Re: Teaching ChatGPT to speak my son’s invented language

#97

Post by melagonster »

Daneel_ wrote: post #90
sharkweek wrote: post #75

Earlier quoted context omitted.

I was trying for 20 minutes to get it to spit out all 50 state capitals with the city names in alphabetical order and it kept doing two things: 1) It'd put the list in alphabetical order by state, but it'd include all the correct capitals 2) It'd list 49 of the 50 capitals, in alphabetical order this time, but duplicating Madison, WI. I'd ask it to try and figure out what it did wrong in both cases, and it'd correctl…

Not here to one-up you, but currently this is just down to how you ask. I came up with this in about a minute: "Please list all 50 US state capital cities, with the list sorted alphabetically starting at the first letter of each line of your response. Please do not create sections for each letter." This returned: - Albany, New York - Annapolis, Maryland - Atlanta, Georgia - Augusta, Maine - Austin, Texas - Baton Roug…

I sure I read this somewhere, more please and thank you offer better output.

the problem is, putting all requirements in one sentence is a rough behaviour, but chatGPT work better in this condition. I always forget this:/

Re: Teaching ChatGPT to speak my son’s invented language

#98

Post by sharkweek »

Daneel_ wrote: post #90
sharkweek wrote: post #75

Earlier quoted context omitted.

I was trying for 20 minutes to get it to spit out all 50 state capitals with the city names in alphabetical order and it kept doing two things: 1) It'd put the list in alphabetical order by state, but it'd include all the correct capitals 2) It'd list 49 of the 50 capitals, in alphabetical order this time, but duplicating Madison, WI. I'd ask it to try and figure out what it did wrong in both cases, and it'd correctl…

Not here to one-up you, but currently this is just down to how you ask. I came up with this in about a minute: "Please list all 50 US state capital cities, with the list sorted alphabetically starting at the first letter of each line of your response. Please do not create sections for each letter." This returned: - Albany, New York - Annapolis, Maryland - Atlanta, Georgia - Augusta, Maine - Austin, Texas - Baton Roug…

Maybe, but I also think it’s fair to assume when you ask it in a much simpler way, “please list all US state capitals in alphabetical order” it should be able to do so.

That isn’t a complicated question that requires much refinement to understand.

To your “please” comment, I also find myself using common niceties probably out of social habit, but also perhaps because in the back of my mind I want the AI that inevitably takes over to remember me being nice to it (half-joking, but also kind of not).

Re: Teaching ChatGPT to speak my son’s invented language

#99

Post by jareklupinski »

jacobsenscott wrote: post #81
crdrost wrote: post #73

Wow, they asked the model to self-evaluate and it just outright cheated: He has three cats. Proposed: h’io’ngkiltrikumrikumrikumri’nguuy Correct: h’io’ngkiltri’ngkumrikumri’nguuy Points: 1 Hypothesis: N/A (Other comments observe that it accidentally compensated for this by getting the sum wrong, haha, d'oh) I have had similar problems with trying to get ChatGPT to do nontrivial things, "here are the rules for this ga…

Chat gpt can't do these things because it doesn't know it is doing anything with a goal. It doesn't know it is playing a game for example. It doesn't know what a game is.

Is giving the system a 'goal' the reason why the DAN prompt with the tokens is effective?

https://github.com/0xk1h0/ChatGPT_DAN

Re: Teaching ChatGPT to speak my son’s invented language

#100

Post by kelseyfrog »

jacobsenscott wrote: post #81
crdrost wrote: post #73

Wow, they asked the model to self-evaluate and it just outright cheated: He has three cats. Proposed: h’io’ngkiltrikumrikumrikumri’nguuy Correct: h’io’ngkiltri’ngkumrikumri’nguuy Points: 1 Hypothesis: N/A (Other comments observe that it accidentally compensated for this by getting the sum wrong, haha, d'oh) I have had similar problems with trying to get ChatGPT to do nontrivial things, "here are the rules for this ga…

Chat gpt can't do these things because it doesn't know it is doing anything with a goal. It doesn't know it is playing a game for example. It doesn't know what a game is.

That's an argument for ChatGPT not being able to do anything a la, "ChatGPT cannot create text because it doesn't understand text," or ChatGPT cannot predict the next word because it doesn't know what words are."

The problem is that it's as powerful a statement as "ChatGPT can't do X because ChatGPT can't do X," which is tautological true.

It's fine that it can't but we don't have epistemological access to know if ChatGPT knows something or not.

Post reply on HN