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

ChatGPT, Rot13, and Daniel Kahneman

jameswillia.ms

Post reply on HN
Print view View original

41–50 of 213 posts

Re: ChatGPT, Rot13, and Daniel Kahneman

#41

Post by uh_uh »

ad404b8a372f2b9 wrote: post #25

Interesting attempt, but if you care to do it much faster it's best to exploit its few-shots learning capabilities and break tasks into sub-tasks rather than trying to talk to it like a human being. That's how I taught it base -10. Here is the single prompt to solve rot13. It still has issues counting lengths. Prompt: a = uryyb pungtcg lbh fghq => [len(i) for i in a.split()] => [5, 7, 3, 4] => len(a.split()) => 4 =>…

It works with your prompt yes, but then I tried a simple example at the end:

  a= Negvsvpvny vagryyvtrapr
  => [len(i) for i in a.split()]
  =>
The solution should be "Artificial intelligence". It never gets it right.

Re: ChatGPT, Rot13, and Daniel Kahneman

#42

Post by e12e »

yunyu wrote: post #19

There's a way simpler answer than this Type I Type II thinking stuff. Most LLMs like GPT are not trained on the level of individual characters – they process input and outputs on the level of subword units that compose multiple characters to support long context windows (i.e. "door" instead of "d", "o", "o", "r"). As a result, they do poorly on character manipulation tasks. You can get some insight here: https://beta…

Hm, could explain why it can't play wordle:

> Give me a five letter word, beginning with e, and having third letter be t. Not including I, l, u or h.

>> etchy

> Does etchy contain h?

>> No, etchy does not contain h.

> which letters do etchy contain?

>> Etchy contains the letters e, t, c, h, and y.

> what were the criteria?

>> The criteria specified that the word must have five letters, begin with e, and have the third letter be t. The word was not allowed to include the letters i, l, u, or h.

> Does the word etchy meet the criteria?

>> Yes, the word etchy meets the criteria because it has five letters, begins with e, has the third letter be t, and does not include the letters i, l, u, or h.

Ed: note that insists that the third letter of etchy is t, not c. From what I've seen both of these errors are typical.

Re: ChatGPT, Rot13, and Daniel Kahneman

#43

Post by christkv »

If they feed this with human interaction based data what will happen if people start massively posting chatGPT content. Will it completely mess up the model over time as it becomes a self referential loop splitting out answers and reinvesting it’s out output?

Re: ChatGPT, Rot13, and Daniel Kahneman

#44

Post by tiziano88 »

yunyu wrote: post #19

There's a way simpler answer than this Type I Type II thinking stuff. Most LLMs like GPT are not trained on the level of individual characters – they process input and outputs on the level of subword units that compose multiple characters to support long context windows (i.e. "door" instead of "d", "o", "o", "r"). As a result, they do poorly on character manipulation tasks. You can get some insight here: https://beta…

This is indeed the most accurate explanation of what's happening

Re: ChatGPT, Rot13, and Daniel Kahneman

#45

Post by tiziano88 »

joshuahedlund wrote: post #9
scarecrw wrote: post #8

I was curious to try this myself. I asked it to encode provided sentences using rot13 and, while it rarely did so correctly, it did produce valid encoded words. Asking it to encode "this is a test sentence" produced: * guvf vf n grfg fvtangher ("this is a test signature") * Guvf vf n grfg zrffntr. ("this is a test message.") * Guvf vf n grfg fnl qrpbqr. ("This is a test say decode.") * guvf vf n grfg fgevat ("this is…

> it did produce valid encoded words I wonder if that's a by-product of some of those words existing on the internet and being part of its training set or somehow close enough in context to show up in its pattern-matching logic, rather than any real "understanding"

Well it's not like GPT3 has any other way of "understanding" anything

Re: ChatGPT, Rot13, and Daniel Kahneman

#46

Post by enlyth »

A lot of people seem to be overlooking the fact that it's missing a huge piece of the puzzle, and that is being able to learn.

This is a model frozen in time, you can explain to it a hundred times why it's wrong and it will learn nothing. Until we have something that learns continuously from more input, I am not impressed

Re: ChatGPT, Rot13, and Daniel Kahneman

#47

Post by ad404b8a372f2b9 »

uh_uh wrote: post #41
ad404b8a372f2b9 wrote: post #25

Interesting attempt, but if you care to do it much faster it's best to exploit its few-shots learning capabilities and break tasks into sub-tasks rather than trying to talk to it like a human being. That's how I taught it base -10. Here is the single prompt to solve rot13. It still has issues counting lengths. Prompt: a = uryyb pungtcg lbh fghq => [len(i) for i in a.split()] => [5, 7, 3, 4] => len(a.split()) => 4 =>…

It works with your prompt yes, but then I tried a simple example at the end: a= Negvsvpvny vagryyvtrapr => [len(i) for i in a.split()] => The solution should be "Artificial intelligence". It never gets it right.

Yeah check my answer to the other reply to this thread, I stopped when I got the answer I wanted and stupidly forgot to test whether it actually worked with any other sentence.

The logic is sound with regards to giving it a few examples and splitting tasks into sub-tasks, that's how they prime their model to evaluate it on all NLP benchmarks in the GPT papers and I've solved many problems like that in ChatGPT.

I've replied to the other comment with a prompt that actually works for any sentence.

Re: ChatGPT, Rot13, and Daniel Kahneman

#48

Post by bravetraveler »

I was showing ChatGPT to my brother and funnily enough, I used ROT13 as a way to demonstrate the neatness

What we got was really interesting. It would give me an encoded phrase and what it believed was the decoded copy. They never matched!

Both were coherent, but completely unrelated. It was really interesting and confusing

Re: ChatGPT, Rot13, and Daniel Kahneman

#49

Post by christkv »

knaik94 wrote: post #15

I was playing around with a similar kind of problem trying to get it to decode Caesar cipher encoded text. I asked it to start by doing a frequency analysis of the ciphertext and for the most part it was right, but counted an extra instance of a letter. From there I tried making it loop through different shift values and made the stop condition finding a real word. It was able to shift by a constant number successful…

I’ve found its ability to lookup algorithms and explain them or generate code to be quite good. It generated a flutter component for me load an image asynchronously that was a great starting point.

It’s definitively a tool I’m willing to pay for to take the drudgery out of coding and I can see it being incredibly useful when learning a new language or framework.

I think stackoverflow is in trouble.

Re: ChatGPT, Rot13, and Daniel Kahneman

#50

Post by uh_uh »

yunyu wrote: post #19

There's a way simpler answer than this Type I Type II thinking stuff. Most LLMs like GPT are not trained on the level of individual characters – they process input and outputs on the level of subword units that compose multiple characters to support long context windows (i.e. "door" instead of "d", "o", "o", "r"). As a result, they do poorly on character manipulation tasks. You can get some insight here: https://beta…

This doesn't really explain it, because the following prompt works flawlessly:

"Print each letter of the word "Artificial intelligence" on a new line. Each line should contain a single letter."

But the following doesn't:

"Print the ROT13 encoding of each letter of the word "Artificial intelligence" on a new line. Each line should contain a single letter."

So it gets hung up specifically on ROT13.

Post reply on HN