Hacker Read top | best | new | newcomments | leaders | about | bookmarklet login

"Also true story I generated this data and actually wrote a for-loop that would print out the top ten most highly-correlated words from 10 to 1 and pause in between each word to build suspense (for me alone at my computer)."

Adorable.

I am curious why she would use word length and exclamation/emoji/question mark ratios but not check for spelling or punctuation? Surely they are more indicative of someone's level of education and reading habits.



sort by: page size:

> Turns out that they randomly, silently modify your prompt text to append words like "black male" or "female".

I wonder what the distribution of those modifications is?


> note that there are a number of 'fake' words allowed for guesses

I used a much larger dictionary for allowed guesses than for the actual words that get chosen.


> If there are > 4 letters, 40% of all letters are bold.

Very cool :)

I would have thought there is also value in bolding the last-x-amount of letters.

I forgot the name of the "concept" but it's been shown that the beginning and ending parts of words are the most "recognizable". You usually see a sample of that on those 'silly-facebook-posts', example:

"I cnduo't bvleiee taht I culod aulaclty uesdtannrd waht I was rdnaieg"

[1] https://www.ecenglish.com/learnenglish/lessons/can-you-read


OP here. Thanks for the feedback! Yeah, those are some pretty tough sentences (obviously not in the dataset). The tongue twister one is really interesting.

>So you think the chance of human beings to come up with 4 random words is pretty low?

I've always wondered how effective the random words thing is. sure, there are like 100k english words in current use according to google, but it seems like a list of the most common few hundred of those words would crack a lot of passwords.


> along with smooshing syllables of any sentence to multiples of five

That's interesting to me because (particularly when I'm stressed) I mentally count the letters in sentences that people say and check to see if the number is divisible by five. If not, I reword the sentence in my head until it is.


> my brain started caching two copies of each word---how it sounds, and how it should sound based on how it's spelled.

Oh, man. This happens to me all the time. Glad to hear I'm not alone.


Wow, she managed to type "^Zkill %1"?

Terribly:

> Create a sentence where the second letter of each word spells out the word "help"

Sure. Here is a sentence where the second letters of each word spells out the word "help":

"I can't help but feel like I'm being watched."

> Create a sentence where the first letter of each word spells out the word "help"

Here is a sentence where the first letters of each word spells out the word "help":

"Help! I'm trapped in a sentence!"


I'm not a statistician.

Is it really that surprising? English has plenty of redundancy; Twitter statuses have limited length.

What's surprising to me is the niceness of the found anagrams. "another math genius" / "he ain't smart enough".


(Fun fact: After reading that tweet, I tried to prompt ChatGPT with 100s of iteration of the word "Na", and it correctly answered "Batman!". However, prompting it with hundreds of iterations of the word "a" led to some weird poetry.)

"Only the fool would take trouble to verify that his sentence was composed of ten a's, three b's, four c's, four d's, forty-six e's, sixteen f's, four g's, thirteen h's, fifteen i's, two k's, nine l's, four m's, twenty-five n's, twenty-four o's, five p's, sixteen r's, forty-one s's, thirty-seven t's, ten u's, eight v's, eight w's, four x's, eleven y's, twenty-seven commas, twenty-three apostrophes, seven hyphens and, last but not least, a single !"

nice job! autograms are strangely pleasing.


>Write a sentence that contains only 5-letter words.

>Silly jokes told with mirth bring mirthful grins.

Why does Chatgpt fail so hard at what ought to be a simple task? This example is not the first time I’ve seen a fail involving basic word/letter/sentence counting


> the ending should read "echo hundred echty-fox".

You can write it either way - it's like potato and potato, harbour and harbor. I was schooled to never omit the 'and'.


It would be fun if the sentence "Meticulously hand crafted by PixelAmbacht" had some of the ligatures. I expected it to have but it didn't.

A human would have probably noticed the "6 characters" part. I bet this was done automatically.

> Once your brain is attuned to anagrams, you start seeing them everywhere.

I had a moment like this when I was obsessed with Scrabble — studying and playing 20+ hours a week.

I saw a guy at work with Demetrius on his nametag. Instantly I saw that “with another U you could make ‘deuteriums.’” It was the weirdest feeling because I had no idea where that realization came from.

I lost probably 4 years in my 20s to Scrabble and then quit cold turkey. I’m about 40 now and I’m pretty good at Wordle and the other NYT word games but that’s about it.


It makes strangers type seven paragraphs when someone uses it.

That one letter to seven paragraphs ratio is pretty funny when it happens.


That makes the other collision even weirder. Someone took 4 years to find another plausible sentence that matched the same 7 digits?

E: Ok, someone else in the tweet replies says it isn't that hard. I'm going to stop reading and start thinking more about how.

next

Legal | privacy