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

81–90 of 212 posts

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

#81

Post by jacobsenscott »

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.

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

#82

Post by wizzwizz4 »

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.

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

#83

Post by roflyear »

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.

Correct. How do so many people get this wrong?

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

#85

Post by joshribakoff »

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.

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.

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

#86

Post by i-use-nixos-btw »

This sounds like a lot of fun! It’s also great that you’re encouraging this - having a passion is great, and following it through to this level is fantastic for development.

I have a question. When you ask an LLM to summarise the rules of the language in a concise manner, and it does so, is it… disheartening?

I mean, if you put a lot of work into creating something, and it gets described in terms that basically make it feel like a configuration - given a glossary and a set of toggles and fill in the blank settings (e.g. word boundaries), out pops a language.

Does seeing that make it feel somewhat less exciting?

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

#87

Post by leereeves »

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…

> "No that's wrong, the game pieces cannot leave the game board,"

Even with approximately all the training data on Earth, ChatGPT still does that with chess.

https://www.youtube.com/watch?v=GneReITaRvs

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

#88

Post by b800h »

dgritsko wrote: post #46

The idea of asking it to produce an "ouroboros prompt" that can be fed back into itself summarizing everything already learned is very clever; definitely going to use that in future ChatGPT sessions of my own.

But it seems like it didn't work in this example..?

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

#89

Post by z3c0 »

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.

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.

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

#90

Post by Daneel_ »

sharkweek wrote: post #75
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…

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 Rouge, Louisiana

- Bismarck, North Dakota

- ...

My gut feeling is that to get what you want from it you need to have a solid understanding of how to manipulate search engines and other fuzzy input systems. On self reflection I find it interesting that I wrote "Please" at the start of each sentence, as if that would give me a better output. Heh.

Post reply on HN