Differentiable Logic Cellular Automata
google-research.github.io
Differentiable Logic Cellular Automata
1–10 of 100 posts
Re: Differentiable Logic Cellular Automata
#2[dead]
Re: Differentiable Logic Cellular Automata
#3[dead]
Re: Differentiable Logic Cellular Automata
#4This writing feels so strongly LLM flavored. It's too bad, since I've really liked Alexander Mordvintsev's other work.
Re: Differentiable Logic Cellular Automata
#5This writing feels so strongly LLM flavored. It's too bad, since I've really liked Alexander Mordvintsev's other work.
Which portion of the text gave you that impression?
Re: Differentiable Logic Cellular Automata
#6This writing feels so strongly LLM flavored. It's too bad, since I've really liked Alexander Mordvintsev's other work.
Which portion of the text gave you that impression?
> To answer this, we'll start by attacking Conway's Game of Life - perhaps the most iconic cellular automata, having captivated researchers for decades
> At the heart of this project lies... > his powerful paradigm, pioneered by Mordvintsev et al., represents a fundamental shift in...
(Not only is this clearly LLM-style, I doubt someone working in a group w/ Mordvintsev would write this)
> Traditional cellular automata have long captivated...
> In the first stage, each cell perceives its environment. Think of it as a cell sensing the world around it.
> To do this, it uses Sobel filters, mathematical tools designed to numerically approximate spatial gradients
Mathematical tools??? This is a deep learning paper my guy.
> Next, the neural network steps in.
...
And it just keeps going. If you ask ChatGPT or Claude to write an essay for you, this is the style you get. I suffered through it b/c again, I really like Mordvintsev's work and have been following this line of research for a while, but it feels pretty rude to make people read this.
Re: Differentiable Logic Cellular Automata
#7I wonder what Stephen Wolfram has to say about this.
Re: Differentiable Logic Cellular Automata
#8Earlier quoted context omitted.
Which portion of the text gave you that impression?
> To answer this, we'll start by attacking Conway's Game of Life - perhaps the most iconic cellular automata, having captivated researchers for decades > At the heart of this project lies... > his powerful paradigm, pioneered by Mordvintsev et al., represents a fundamental shift in... (Not only is this clearly LLM-style, I doubt someone working in a group w/ Mordvintsev would write this) > Traditional cellular automa…
The reason LLMs write like that is, unsurprisingly, that some people write like that. In fact many of them do - it's not uncommon.
If you have proof like the logits are statistically significant for LLM output, that would be appreciated - otherwise it's just arguing over style.
Re: Differentiable Logic Cellular Automata
#9I wonder what Stephen Wolfram has to say about this.
I wish John Conway was still around to comment.
Re: Differentiable Logic Cellular Automata
#10Earlier quoted context omitted.
> To answer this, we'll start by attacking Conway's Game of Life - perhaps the most iconic cellular automata, having captivated researchers for decades > At the heart of this project lies... > his powerful paradigm, pioneered by Mordvintsev et al., represents a fundamental shift in... (Not only is this clearly LLM-style, I doubt someone working in a group w/ Mordvintsev would write this) > Traditional cellular automa…
The reason LLMs write like that is, unsurprisingly, that some people write like that. In fact many of them do - it's not uncommon. If you have proof like the logits are statistically significant for LLM output, that would be appreciated - otherwise it's just arguing over style.
I've read a _lot_ of deep learning papers, and this is extremely atypical. I agree with you that if there were any sort of serious implications then it'd be important to establish proof, but in the case of griping on a forum I think the standard of evidence is much lower.