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

161–170 of 250 posts

Re: I Taught ChatGPT to Invent a Language

#161

Post by macrolime »

seydor wrote: post #112
uvbu wrote: post #107

Earlier quoted context omitted.

Pretty sure it gets the entire conversation as input

Is this described somewhere? Wikipedia doesn't help

It preserves context by taking using the whole context as input. On the section "one difference from BERT" here it is described a bit more how this works, including some nice animations.

http://jalammar.github.io/illustrated-gpt2/

It uses both its own output from previous steps and the users prompt(s) as input for each token(word) that it predicts.

Re: I Taught ChatGPT to Invent a Language

#163

Post by ElevenLathe »

Robotbeat wrote: post #158
ElevenLathe wrote: post #155

Earlier quoted context omitted.

I tried to play rock paper scissors against it, but it kept insisting that paper beats scissors. Never did convince it otherwise.

Did you tell it to “play correctly with the standard rules”?

I did, it even volunteered what those rules were, but when I asked it to keep a running score it always scored it as if paper beat scissors.

Re: I Taught ChatGPT to Invent a Language

#164

Post by Robotbeat »

_yb2s wrote: post #152

[flagged]

I could immediately tell this was made by ChatGPT because I had spent last night doing the same thing, generating finger-wagging diatribes in ChatGPT about how being anxious about AI is racist, etc, etc…

There is a sort of style typically used in this sort of thing, even with prompting, that sounds a bit like low effort high school English assignments… (but would fool someone not familiar with ChatGPT).

Re: I Taught ChatGPT to Invent a Language

#165

Post by jrmg »

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 asked how to configure something in PlatformIO and it told me it was possible to do exactly what I wanted, and gave me easy to use syntax with full examples and explanation. When I questioned it further, it pointed me to the URLs of docs covering the feature.

None of it was in any way real - the feature I wanted does not actually exist.

Re: I Taught ChatGPT to Invent a Language

#166

Post by _frkl »

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 had a similar experience where I asked it to tell me about creating a GUI with nim, and it told me to use the 'forms' module from the standard library, and the example code it printed was showing an easy to use and nice API. Took me a while to realise it wasn't my fault that I couldn't find any documentation about it, anywhere....

Re: I Taught ChatGPT to Invent a Language

#167

Post by Robotbeat »

lordnacho wrote: post #151
seydor wrote: post #51

Earlier i was saying it isn't scary but maybe it is. It is impressive how ChatGPT keeps track of state and the flow of the conversation. How does it do it? Is it some kind of memory or some other model? ( I asked it, it keeps lying to me that it does not have memory)

I don't get it either, I tried to have a conversation where it needed to remember something rather simple, but it didn't seem to get it: > Let's pretend you are Danish [Ok] > What's the name of the highest point in your country, in the local language? Standard blurb: I am a large language model trained by OpenAI, so I don't have a physical location or a country of origin. I exist as a virtual entity, and I am designe…

You’re triggering one of its sort of canned responses, and you need to be subtle about how to get around it. Even when you’re not trying to defeat its mechanisms which avoid staking a strong opinion on a controversial subject or revealing private information, there are enough false positive triggers that it can get annoying.

Re: I Taught ChatGPT to Invent a Language

#168

Post by fnordpiglet »

furyofantares wrote: post #144
fnordpiglet wrote: post #67

Earlier quoted context omitted.

I don’t think their goal was to make a slime language called Glorp. If it were, I’m sure you’re absolutely right they could have done it without breaking a sweat. But try this, get your laptop out and start typing into its prompt to create a new language for slimes and see how much longer it takes you. That’s the amazing part - that a general purpose program is able to do the exercise at all with no training, special…

I agree with you, and it's amazing. But the claim was that it's an example of how much more you can get done with ChatGPT when it seems like an example where the author got a lot less done than they would have with notepad.exe

But this isn’t an example of that it’s an example of “wow that’s amazing”

In the realm of getting a lot more stuff done, I’ve been using it as a companion to explain a new language I’m learning right now. It’s super useful to ask it about language constructs, idiomatic ways to do X, is this way of doing Y good, etc. It’s saved me hours of using Kagi to soft through semi relevant pages stuffed with SEO and ancient answers from stackoverflow that are completely irrelevant other than a few matched key words.

Re: I Taught ChatGPT to Invent a Language

#169

Post by fnordpiglet »

Miraste wrote: post #134
Oxidation wrote: post #73

Earlier quoted context omitted.

> some of these gaps can be tackled Seems like the major gap is in facts. It'll often make up completely plausible specific details that are flat wrong, or refuse to proceed if it's "not allowed" to do so. Coupling it (handwave) with a massive structured data repository like Wolfram Alpha and Wikidata would be really something.

It insisted to me for a while that the sun was red. The "guardrails" do nothing to stop it from lying confidently about almost everything.

I’ve only seen it do stuff like that if I assert a false premise and ask it questions off the false premise.

Re: I Taught ChatGPT to Invent a Language

#170

Post by just4nornies »

elcomet wrote: post #159
just4nornies wrote: post #105

Earlier quoted context omitted.

At first, there was no output. After maybe 3-4 minutes it displayed "An error occurred ... contact help etc" message. I waited about 30 seconds then tried again and it said that was too fast. So I waited a whole minute and tried again and it immediately spat out the "An error occurred" message. To me, the idea that it crashed stuck with me because of how it streams its output, which was empty for 3-4 minutes on the f…

It has nothing to do with your prompt. The site is just overloaded. It takes the same amout of time for every prompt, no matter it's complexity or simplicity, it's just the length that matters.

Well, I haven't been able to get an answer. It always get stuck at that question and then an error message. Something is definitely wrong but I can't debug it on HN... so
Post reply on HN