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

211–220 of 250 posts

Re: I Taught ChatGPT to Invent a Language

#211

Post by wvenable »

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…

For me, it made up software packages to do what I needed to do.

I also tried to have it generate some 6502 assembly to multiply two numbers and generated an iterative add approach that failed to do any adds. So I informed it that it forgot to add and it realized it's mistake and corrected the code.

I tried to get it to optimize further and it generated some code using shifts that I really need to double check. It also generated a table-based method that was woefully incomplete. As I continued to get it to correct the table function, it was clear it didn't really understand 6502 assembly that well.

But I've pasted large block of C# code and then gave it sample data and it understood the code well enough to generate the correct results of the code.

Re: I Taught ChatGPT to Invent a Language

#212

Post by fpgaminer »

jameshart wrote: post #210
fpgaminer wrote: post #184

Earlier quoted context omitted.

From the ChatGPT announcement post: > ChatGPT sometimes writes plausible-sounding but incorrect or nonsensical answers. Fixing this issue is challenging, as: (1) during RL training, there’s currently no source of truth; (2) training the model to be more cautious causes it to decline questions that it can answer correctly; and (3) supervised training misleads the model because the ideal answer depends on what the mode…

Yes, this is indeed a known limitation. So the other day, chatGPT was doing a great job acting as a trivia quizmaster for me when it casually threw out the 'fact' that Pope Francis was the first South American to be elected pope, and that he served in the role from 2013 until his death in 2017. (For the avoidance of doubt: Pope Francis is still alive). I think we can all understand how that sort of thing counts as 'p…

> 'rich and internally consistent novel programming language semantics with fully worked examples of applications, and rich explanations of how they work'.

Oh for sure, that is a really cool finding. Didn't mean to negate that, just provide a little context.

Re: I Taught ChatGPT to Invent a Language

#213

Post by whymauri »

Miraste wrote: post #124
whymauri wrote: post #98

Earlier quoted context omitted.

I asked it to simulate a Chess engine and it gave the usual "I am a blah blah blah, I cannot blah blah blah, because blah blah." I clicked "Try Again" and it worked.

Is it any good?

It's alright when it remembers the move sequence, which it usually doesn't past ~5 moves.

But, asking it to simulate a chess engine, a chess book, or a famous player performs better overall, especially in the opening. It also helps to request that it do not draw the board, but rather re-iterate the moves seen so far. And when simulating an engine or book, it provides logic for its move. But it can get into a loop where it gives the same explanation for each move deeper into the game.

Without tweaking, it probably plays 300 ELO with the occasional invalid move. With tweaking, maybe 600-700 ELO. Strongest performance in the opening.

Re: I Taught ChatGPT to Invent a Language

#214

Post by uoaei »

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…

Congrats, you have just made a successful logical argument against intellectual property per se!

Re: I Taught ChatGPT to Invent a Language

#216

Post by bo1024 »

yreg wrote: post #181

OP, this part of the article contains a mistake, right? > I will provide English sentences, and you will provide their translation into Glorp. Gloop slog sploma slurpi. Gloop splog slopa slurpi. > Sure, here are the translations of the given sentences into Glorp: > 1. "Gloop slog sploma slurpi" - This sentence means "The slime smells the food with its mouth" in Glorp. That is a translation from Glorp to English, not…

I wondered the same thing. Quite strange that both the author and ChatGPT made the same mistake.

Re: I Taught ChatGPT to Invent a Language

#217

Post by shagie »

harshalizee wrote: post #202
shagie wrote: post #191

Earlier quoted context omitted.

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…

A little hint for parsing Day5 -- Regex is your friend.

I didn't have a problem with it... but its a "how do you get to the spot where its mostly bug fixing using ChatGPT and prompts?"

For that repo (not mine - mine is over at https://github.com/shagie/AoC_2022 ), day 5 is where they got to the point where the complexity of the description of the problem is greater than the complexity of the problem itself.

Re: I Taught ChatGPT to Invent a Language

#219

Post by TrueGeek »

lgas wrote: post #179
jrmg wrote: post #165

Earlier quoted context omitted.

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.

> the feature I wanted does not actually exist. Did you try asking it to implement it?

Tomorrow on HN: "GitHub no longer accepting PR from ChatGPT"

Re: I Taught ChatGPT to Invent a Language

#220

Post by nsxwolf »

So everything I just read in this article... it all came from a model that just "predicts the word most likely to come next"... that's it? None of this was intentional? I don't know how you begin to comprehend what this thing is or how it was created.
Post reply on HN