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

I Taught ChatGPT to Invent a Language

maximumeffort.substack.com

Post reply on HN
Print view View original

191–200 of 250 posts

Re: I Taught ChatGPT to Invent a Language

#191

Post by shagie »

codetrotter wrote: post #142
rikroots wrote: post #129

Earlier quoted context omitted.

Tempting, but no. I'm too busy failing at Advent of Code to start playing with chatgpt today.

Tell ChatGPT to solve Advent of Code for you :D Like so, https://video.nstr.no/w/6z7PxB4J92H3NHhgMmfYVw

The advent of code problems have gotten beyond the "easy to solve" category. Days 5 and 6 have gotten more tricky.

https://github.com/ishan0102/aoc-2022-chatgpt

> Day 5: Supply Stacks

> This day actually threw me for a loop because parsing the input is so challenging. After spending a while on prompting I wasn't able to produce anything meaningful. I might actually stop after today if the puzzles keep getting harder because I don't want to spend all this time messing with input parsing. This highlights some of the limitations well, we still need human input to coax the model into understanding how to break down a hard problem.

Re: I Taught ChatGPT to Invent a Language

#192

Post by nadavr »

OJFord wrote: post #123
nadavr wrote: post #116

Earlier quoted context omitted.

Why isn't this a relex? As an interested casual linguistics observer, that's what it looks like to me. Is it just because the nouns are inflected?

Easiest reason is the 'introduction particle', blub which we don't have in English, for subordinate clauses. I think 'taught ChatGPT to invent a' is hyperbolic though, this is more like 'taught ChatGPT my invented' - the only thing it invents itself are the 'relex' word->word mappings.

Isn't `blub` more or less equivalent to `that` or `which`?

Re: I Taught ChatGPT to Invent a Language

#193

Post by just4nornies »

layer8 wrote: post #185
just4nornies wrote: post #64

Ask #ChatGPT to list all ways to do X If it misses a way you know then ask if it knows about it If it confirms, ask it why it didn't include it In my case, it crashed (on two such attempts with different questions, happy to share) It seems to recall answers it has seen but not able to expand on those answers with knowledge it already has That's because it does not have knowledge. It has a bunch of correlations, encod…

I couldn’t reproduce that. E.g.: List all the ways to die. Accident or injury Heart attack or stroke Cancer Respiratory failure Suicide Drug overdose Dehydration Blood loss Infection or disease Natural disasters Violence or homicide Drowning Starvation or malnutrition Electrocution Hypothermia or heat stroke Falling Asphyxiation Animal attack Human or animal disease Old age or organ failure. Do you know of SIDS as a…

Nice.

So it was producing an error on every attempt. I will try again.

My bigger point is the limits of statistical learning. What if you asked it again in the same session will it include SIDS? I can't try right now, ChatGPT is not responding.

How about in a different session? Will it include it? (obviously not, since it's training is not continual)

Also, what if you asked it something with fewer possibilities? like list all the ways encrypted TLS traffic on the Internet can be captured by attackers. In my case, when I tried that, it left out quite a few ways, one was BGP attacks. But there are only so many known ways for an attacker to capture TLS traffic, unlike ways of dying.

There is a limitation to statistical learning. It's not ontological and it's not epistemological. It's purely statistical.

That's what I'm getting at. The fact that it crashed at the right moment was funny, but in retrospect coincidental.

Re: I Taught ChatGPT to Invent a Language

#196

Post by s1mon »

jameshart wrote: post #149

I would definitely question who is doing the inventing here. However, I had an experience with chatGPT yesterday that definitely felt like it actually inventing. Problem is, I didn’t ask it to. I was seeing how much it knew about HyperTalk, the scripting language used in HyperCard. And it was surprisingly well informed. But it also told me that one of the interesting things about HyperTalk was its ‘message stack’ sys…

I've asked ChatGPT several times about FeatureScript [0], which is a language used to create features in the cloud based 3D CAD software, Onshape. It will happily invent syntax and code that has almost nothing to do with how FeatureScript is written. When confronted with this, it will admit that it made stuff up and doesn't know much about Onshape or FeatureScript.

[0] https://cad.onshape.com/FsDoc/index.html

Re: I Taught ChatGPT to Invent a Language

#197

Post by jameshart »

arcturus17 wrote: post #186
jameshart wrote: post #149

I would definitely question who is doing the inventing here. However, I had an experience with chatGPT yesterday that definitely felt like it actually inventing. Problem is, I didn’t ask it to. I was seeing how much it knew about HyperTalk, the scripting language used in HyperCard. And it was surprisingly well informed. But it also told me that one of the interesting things about HyperTalk was its ‘message stack’ sys…

> I would definitely question who is doing the inventing here. > But also, potentially a fruitful line to explore would be having chatGPT collaborate on designing new programming language ideas. It's the same in your example... It invented but you guided it with extremely deep domain knowledge. I know nothing about HyperCard and wouldn't have been able to make anything out of anything you just described.

No, the concept of a 'message stack' was something it came up with. When I asked it for more details it confidently supplied them, including what it was used for, and how it worked. Then I just asked it to show me it in a script, and... it was happy to oblige. It was making it up as it went along, all I was doing was taking it at its word and asking questions.

It is like the world's most committed improv partner. It will agree and add forever.

Re: I Taught ChatGPT to Invent a Language

#200

Post by layer8 »

just4nornies wrote: post #193
layer8 wrote: post #185

Earlier quoted context omitted.

I couldn’t reproduce that. E.g.: List all the ways to die. Accident or injury Heart attack or stroke Cancer Respiratory failure Suicide Drug overdose Dehydration Blood loss Infection or disease Natural disasters Violence or homicide Drowning Starvation or malnutrition Electrocution Hypothermia or heat stroke Falling Asphyxiation Animal attack Human or animal disease Old age or organ failure. Do you know of SIDS as a…

Nice. So it was producing an error on every attempt. I will try again. My bigger point is the limits of statistical learning. What if you asked it again in the same session will it include SIDS? I can't try right now, ChatGPT is not responding. How about in a different session? Will it include it? (obviously not, since it's training is not continual) Also, what if you asked it something with fewer possibilities? like…

What ChatGPT remembers within a session is certainly limited (there’s probably a resource quota per session), and it will eventually “forget”. The actual underlying model is not modified, and you are totally right that it’s just statistical. It’s only useful for use cases where that’s fine.

ChatGPT currently errors out a lot for me as well, I think they’re being overwhelmed by requests.

Post reply on HN