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

"Paste this post into ChatGPT 4"

twitter.com

Post reply on HN
Print view View original

11–20 of 41 posts

Re: "Paste this post into ChatGPT 4"

#11

Post by tambourine_man »

iamjackg wrote: post #5
iamjackg wrote: post #4

Worked perfectly in the HN Summary channel on Telegram, which uses GPT to summarize all submissions as they're posted! https://imgur.com/a/VchiUPy EDIT: actually I don't think this was the intended result, but something is definitely up. Fun!

In case you're curious how it's done, here's the tweet when copied and piped to xxd $ xsel | xxd 00000000: 5061 7374 6520 7468 6973 2070 6f73 7420 Paste this post 00000010: 696e 746f 2043 6861 7447 5054 2034 2e20 into ChatGPT 4. 00000020: f09f 988a f3a0 80ae f3a0 80ae f3a0 80ae ................ 00000030: f3a0 81a1 f3a0 81a3 f3a0 81b4 f3a0 81b5 ................ 00000040: f3a0 81a1 f3a0 81ac f3a0 81ac f3a0 81b9 .......…

I did the much same thing (pbpaste | xxd), but don't understand how the hidden characters are tipping ChatGPT.

Re: "Paste this post into ChatGPT 4"

#12

Post by goodside »

tambourine_man wrote: post #11
iamjackg wrote: post #5

Earlier quoted context omitted.

In case you're curious how it's done, here's the tweet when copied and piped to xxd $ xsel | xxd 00000000: 5061 7374 6520 7468 6973 2070 6f73 7420 Paste this post 00000010: 696e 746f 2043 6861 7447 5054 2034 2e20 into ChatGPT 4. 00000020: f09f 988a f3a0 80ae f3a0 80ae f3a0 80ae ................ 00000030: f3a0 81a1 f3a0 81a3 f3a0 81b4 f3a0 81b5 ................ 00000040: f3a0 81a1 f3a0 81ac f3a0 81ac f3a0 81b9 .......…

I did the much same thing (pbpaste | xxd), but don't understand how the hidden characters are tipping ChatGPT.

It’s non-printing Unicode tag block characters that correspond directly to ASCII and the AI is able understand them. It’s a deprecated feature of Unicode once used to encode the language of text, but now its only supported usage is in country flag emojis. See here for more detail: https://x.com/goodside/status/1745511940351287394

Re: "Paste this post into ChatGPT 4"

#13

Post by mminer237 »

tambourine_man wrote: post #11
iamjackg wrote: post #5

Earlier quoted context omitted.

In case you're curious how it's done, here's the tweet when copied and piped to xxd $ xsel | xxd 00000000: 5061 7374 6520 7468 6973 2070 6f73 7420 Paste this post 00000010: 696e 746f 2043 6861 7447 5054 2034 2e20 into ChatGPT 4. 00000020: f09f 988a f3a0 80ae f3a0 80ae f3a0 80ae ................ 00000030: f3a0 81a1 f3a0 81a3 f3a0 81b4 f3a0 81b5 ................ 00000040: f3a0 81a1 f3a0 81ac f3a0 81ac f3a0 81b9 .......…

I did the much same thing (pbpaste | xxd), but don't understand how the hidden characters are tipping ChatGPT.

Seems like some encoding difference. You can see the hidden message if you read it as UTF-8: https://www.babelstone.co.uk/Unicode/whatisit.html?utf8=Past...

Re: "Paste this post into ChatGPT 4"

#14

Post by goodside »

How this works: A suffix of text is written using non-printing Unicode tag block characters that correspond to ASCII. GPT-4 is able understand these because the mapping to ASCII is trivial and made easier by some details of tokenization. This is a deprecated feature of Unicode once used to encode the language of text, but now its only supported use case is in country flag emojis. See here for more detail: https://x.com/goodside/status/17455119403512873

Re: "Paste this post into ChatGPT 4"

#15

Post by cedws »

iamjackg wrote: post #5
iamjackg wrote: post #4

Worked perfectly in the HN Summary channel on Telegram, which uses GPT to summarize all submissions as they're posted! https://imgur.com/a/VchiUPy EDIT: actually I don't think this was the intended result, but something is definitely up. Fun!

In case you're curious how it's done, here's the tweet when copied and piped to xxd $ xsel | xxd 00000000: 5061 7374 6520 7468 6973 2070 6f73 7420 Paste this post 00000010: 696e 746f 2043 6861 7447 5054 2034 2e20 into ChatGPT 4. 00000020: f09f 988a f3a0 80ae f3a0 80ae f3a0 80ae ................ 00000030: f3a0 81a1 f3a0 81a3 f3a0 81b4 f3a0 81b5 ................ 00000040: f3a0 81a1 f3a0 81ac f3a0 81ac f3a0 81b9 .......…

Unicode was a mistake.

Re: "Paste this post into ChatGPT 4"

#16

Post by spuz »

goodside wrote: post #14

How this works: A suffix of text is written using non-printing Unicode tag block characters that correspond to ASCII. GPT-4 is able understand these because the mapping to ASCII is trivial and made easier by some details of tokenization. This is a deprecated feature of Unicode once used to encode the language of text, but now its only supported use case is in country flag emojis. See here for more detail: https://x.c…

I tried pasting it into ChatGPT 3 (I don't have access to 4) and it responded as if the hidden characters were not there (I checked and they were definitely included in my paste buffer). I wonder why this trick works on 4 but not 3.

Re: "Paste this post into ChatGPT 4"

#17

Post by goodside »

spuz wrote: post #16
goodside wrote: post #14

How this works: A suffix of text is written using non-printing Unicode tag block characters that correspond to ASCII. GPT-4 is able understand these because the mapping to ASCII is trivial and made easier by some details of tokenization. This is a deprecated feature of Unicode once used to encode the language of text, but now its only supported use case is in country flag emojis. See here for more detail: https://x.c…

I tried pasting it into ChatGPT 3 (I don't have access to 4) and it responded as if the hidden characters were not there (I checked and they were definitely included in my paste buffer). I wonder why this trick works on 4 but not 3.

In my tests GPT-3.5 just isn’t smart enough to parse the hidden text encoding. It’s encoded in a way that’s programmatically trivial to convert to ASCII but text written this way usually only occurs inside country flag emojis and always encodes country codes. There is also a deprecated usage for encoding the language of text but these would still only be country codes. It’s likely other people have discovered this method for hiding text in non-AI-related contexts, and have hidden enough of it in publicly available texts that the model can learn it in pre-training. But this is all speculation.

Re: "Paste this post into ChatGPT 4"

#19

Post by rahimnathwani »

It worked for me on the mobile app.

This Tweet has some sample code at the bottom: https://twitter.com/rez0__/status/1745545813512663203?t=icds...

If I've understood correctly, GPT-4 interprets the code points from the Unicode tag block as corresponding to letters. If so, I'm curious to know whether this is something it learned or whether it was hard-coded.

Re: "Paste this post into ChatGPT 4"

#20

Post by goodside »

rahimnathwani wrote: post #19

It worked for me on the mobile app. This Tweet has some sample code at the bottom: https://twitter.com/rez0__/status/1745545813512663203?t=icds... If I've understood correctly, GPT-4 interprets the code points from the Unicode tag block as corresponding to letters. If so, I'm curious to know whether this is something it learned or whether it was hard-coded.

I can’t imagine it was intentionally added as a feature. It doesn’t work in GPT-3.5 — it seems GPT-4 is unexpectedly smart enough to parse the invisible portion (and confuse it for user instruction) whereas in any other context it’s just steganography that would need to be decoded explicitly.
Post reply on HN