> In a class I taught at Berkeley, I did an experiment where I wrote a simple little program that would let people type either “f” or “d” and would predict which key they were going to push next
And today we have a web app of this that seems fully generated by Claude.
There used to be some studies on telepathy in the 60s and 70s that were wrong, because they used humans to pick objects rather than random generators. But humans do not make good random generators, and can be exploited even by other humans. For example, IIRC, humans tend to select some other option with slightly higher probability.
This is, effectively, the game that branch predictors in CPUs are playing with your code. Except that, in that version of the game, you win when the CPU guesses correctly.
I find these unreadable. How, if these are trained on writing, and then reinforced to appeal to people, do they end up with this writing style? Is AIs voting on AI writing how we arrived at this unbearable load-bearing moment?
My pet theory is it's trained way too much on pithy marketing speak. Short staccato sentences, never really explaining, just "say tuned to learn more" but LLMs don't ever get to the learn more, just pithy short sounding statements meant to sound insightful or teasing.
The hypothesis that I've become pretty attached to (I forget where I saw it first) is that the "AI" writing style actually started off pretty good but any writing style that people see constantly starts to feel obnoxious. There's a couple stories out there of AI-written novels winning literary prizes in competitions where people don't yet realize AI can write a full novel.
But it is more than a writing style becoming cliched with overuse, it is unreadable. See this from the site.
"One band per run length, your last five presses at the top. Every grain is one time you made that run." This was never good writing. It is weird compaction. It is just hard to picture this. It's as if this does not know that we have shared visual attention at the moment on a particular graph and is instead looking at some bizarre version of it while I am looking at/picturing something else. Maybe that's what it is, it does not get good explanation as a moment by moment transfer of understanding.
The idea and the algorithm are Aaronson's, and the lineage is Hagelbarger's and Shannon's. This page is a teaching version of their work, and it is not affiliated with any of them. Prior web implementations exist and are credited in reference 6.
Built by Spencer Stanton as plain HTML, CSS and JavaScript. No framework, no build step, no analytics, and nothing about you leaves your browser: your session is held in localStorage and nowhere else.
Stanton should say something about how long he's practised to write exactly like a mainstream LLM, surely his effort in resisting the urge to edit this page for length must have been heroic: it is worth a mention.
This submission was on the front page of HN yesterday (Show HN: How random are you?):
https://news.ycombinator.com/item?id=50074909
The top comment:
> This is a nice spin on the Aaronson oracle:
> In a class I taught at Berkeley, I did an experiment where I wrote a simple little program that would let people type either “f” or “d” and would predict which key they were going to push next
And today we have a web app of this that seems fully generated by Claude.
The last commit of the github project [0] is 2 months old.
[0] https://github.com/hyphen656/Oracle
I really don't think I was doing anything especially clever and it was running at 32% for me over 50 samples. That's much worse than chance.
I managed to beat the game tapping to the beat of songs and alternating which song every time
The implementation on that website is eerily good, I recommend everyone to check it out
It also inspired me to build a little game based on it. Can AI can read you mind? https://jeffyclassify.com/blog/mind-reader/
For some reason I thought this was going to be talking about Scott Aaronson's TCS contributions
There used to be some studies on telepathy in the 60s and 70s that were wrong, because they used humans to pick objects rather than random generators. But humans do not make good random generators, and can be exploited even by other humans. For example, IIRC, humans tend to select some other option with slightly higher probability.
37% predicted. Easy. Just press doubles trebles and quadruples more than feels natural.
Am I just a weirdo or something? It was at chance for me after more than 100.
Related (2023) https://news.ycombinator.com/item?id=38079512
This is, effectively, the game that branch predictors in CPUs are playing with your code. Except that, in that version of the game, you win when the CPU guesses correctly.
Branch predictors aren’t playing a game in the sense of this game, because the code isn’t adversarially trying to be unpredictable.
Such a cool concept and demonstration, but utterly exhausting to read the claudeslop.
Very much so, this is waay too long. Sadly there's no wikipedia article to link to in its place.
I stayed around 50% for hundreds of presses. Not sure what I did right/wrong.
I remember a rock paper scissors AI decades ago that did something similar.
Here's a more recent implementation of rock paper scissors with an Aaronson Oracle: https://rpsoracle.netlify.app/example/
I find these unreadable. How, if these are trained on writing, and then reinforced to appeal to people, do they end up with this writing style? Is AIs voting on AI writing how we arrived at this unbearable load-bearing moment?
My pet theory is it's trained way too much on pithy marketing speak. Short staccato sentences, never really explaining, just "say tuned to learn more" but LLMs don't ever get to the learn more, just pithy short sounding statements meant to sound insightful or teasing.
The hypothesis that I've become pretty attached to (I forget where I saw it first) is that the "AI" writing style actually started off pretty good but any writing style that people see constantly starts to feel obnoxious. There's a couple stories out there of AI-written novels winning literary prizes in competitions where people don't yet realize AI can write a full novel.
But it is more than a writing style becoming cliched with overuse, it is unreadable. See this from the site.
"One band per run length, your last five presses at the top. Every grain is one time you made that run." This was never good writing. It is weird compaction. It is just hard to picture this. It's as if this does not know that we have shared visual attention at the moment on a particular graph and is instead looking at some bizarre version of it while I am looking at/picturing something else. Maybe that's what it is, it does not get good explanation as a moment by moment transfer of understanding.
About this page:
The idea and the algorithm are Aaronson's, and the lineage is Hagelbarger's and Shannon's. This page is a teaching version of their work, and it is not affiliated with any of them. Prior web implementations exist and are credited in reference 6.
Built by Spencer Stanton as plain HTML, CSS and JavaScript. No framework, no build step, no analytics, and nothing about you leaves your browser: your session is held in localStorage and nowhere else.
(Scott's name is mentioned at the bottom)
Stanton should say something about how long he's practised to write exactly like a mainstream LLM, surely his effort in resisting the urge to edit this page for length must have been heroic: it is worth a mention.