msuvakov

It’s striking how ending of the story mirrors Roger Penrose’s conformal cyclic cosmology, where the heat death of one universe mathematically resets through conformal scaling to become the big bang of the next.

I played (vibe coded) around with the CDC records and the results look easily reproducible. Here it is in my vibe gallery: https://suvakov.github.io/vibes/AlzheimerMortalityByOccupati...

I had a similar idea inspired by xkcd:

https://suvakov.github.io/vibes/SlidingPuzzleChess/index.htm...

Why the b > 2 condition? In the b=2 case, all three formulas also work perfectly, providing a ratio of 1. And this is interesting case where the error term is integer and the only case where that error term (1) is dominant (b-2=0), while the b-2 part dominates for larger bases.

To put it this way: after seeing examples of how a LLM with similar capabilities to state-of-the-art ones can be built with 20 times less money, we now have proof that the same can be done with 20 times more money as well!

Thanks. It seems that some UTF-8 characters are not accepted as part of the comment. Anyone who wants to see the rabbit should check the page source :)

      ___                        ___                     ___           ___     
     /  /\           ___        /  /\      ___          /  /\         /  /\    
    /  /::|         /__/\      /  /:/     /__/\        /  /::\       /  /::\   
   /  /:|:|         \__\:\    /  /:/      \  \:\      /  /:/\:\     /__/:/\:\  
  /  /:/|:|__       /  /::\  /  /:/        \__\:\    /  /:/  \:\   _\_ \:\ \:\ 
 /__/:/_|::::\   __/  /:/\/ /__/:/         /  /::\  /__/:/ \__\:\ /__/\ \:\ \:\
 \__\/  /~~/:/  /__/\/:/~~  \  \:\        /  /:/\:\ \  \:\ /  /:/ \  \:\ \:\_\/
       /  /:/   \  \::/      \  \:\      /  /:/__\/  \  \:\  /:/   \  \:\_\:\  
      /  /:/     \  \:\       \  \:\    /__/:/        \  \:\/:/     \  \:\/:/  
     /__/:/       \__\/        \  \:\   \__\/          \  \::/       \  \::/   
     \__\/                      \__\/                   \__\/         \__\/

Not sure. I am using models/API keys from https://aistudio.google.com. They just added new models, e.g., gemini-2.0-pro-exp-02-05. Exp models are free of charge with some daily quota depending on model.

Gemini 2.0 works great with large context. A few hours ago, I posted a ShowHN about parsing an entire book in a single prompt. The goal was to extract characters, relationships, and descriptions that could then be used for image generation:

https://news.ycombinator.com/item?id=42946317

Great observations! Thanks for your deep dive into result. I didn't go into this level of detail myself, but one thing I notice is that "the cat" in the graph is actually Peter, the cat that Tom gave painkiller to (with missing connections to Tom and Aunt Polly).

You're absolutely right that some characters are missing even in those short books, and there are likely many more relationships that haven't been fully captured. That said, I’m still quite impressed by how much data the LLM extracted in a single pass, especially given the complexity of the task, the size of the input, and the strict output format.

My estimate of quality was subjective. To truly quantify accuracy, we’d need to establish a "ground truth" with a better approach and measure the difference between the generated and actual relationship graphs. One possible way to do that would be to process the text in multiple passes: first extracting characters, then identifying relationships, both steps with more sophisticated prompt engineering. Another way is to manually annotate the network. The only book I found with a publicly available, human-annotated character network is Les Misérables, based on Donald Knuth’s work: https://github.com/MADStudioNU/lesmiserables-character-netwo...

However, there is an additional challenge. Even with human annotation, the question remains: how to define relationship network? What is a relationship in a book? Should it be limited to explicitly stated connections in the text, or it also can include deduced relationships based on context with some probability? Defining these criteria is crucial to quantify quality of the result.

Same in Serbo-Croatian: 1 mačka 2-4 mačke 5+ mačaka 0 mačaka

This news should be dated back in December, not now.

The T2T team published a preprint [1] last December and released the data [2] in March. However, due to the peer review process, the findings have only just been formally published in Nature. The publication timeline can indeed be slow, and in cases like this one, the question is: what's the point when all scientists interested in the topic already know about it and working with this assembly?

[1] https://www.biorxiv.org/content/10.1101/2022.12.01.518724v1.... [2] https://github.com/marbl/CHM13

I forked it with similar idea: https://openprocessing.org/sketch/1929687

No, that is the weak point of this system. Anyone can change date in pdf and no one can check that except Serbian authorities. The only limit for date is one year after test because verification system (qr code link) is set not to validate older tests.

They probably generate ID when results are stored in database, not when samples are taken. Difference in processing time explains this. What are the dates of result (stated at the bottom of the pdf)?

Updated plot (29 test data from volontiers) is available here: https://twitter.com/msuvakov/status/1481033480901431297

Only outlier is Djokovic's positive test. It perfectly fits to 26. December, the same date timestamp was created.

More precisely a quarter:

38 million km2 (Moon area) : 150 million km2 (land area of the Earth) = 25%

It should be:

  def tail_factorial(n, accumulator=1):
    if n == 0: return accumulator
    else: return tail_factorial(n-1, accumulator * n)

Primecoin is an example: https://primes.zone

Cool but old. It can be done in any number base, e.g. in decimal: https://www.youtube.com/watch?v=fQQ8IiTWHhg