Chains of Affection: The Structure of Adolescent Romantic and Sexual Networks

#Papers
@Dagmawi_Babi

Here is the research paper
• https://t.me/c/1156511084/813

Let's not even talk about how they trained it without human supervision on unlabelled videos. AND it scaled well as they increased GPUs which most LLMs don't.

#Google #Genie #AI #Papers
@Dagmawi_Babi

Just finished reading the paper, Attention is All You Need, that introduced transformer neural network models that gave rise to all the LLMs & gen AI we know of today.
• https://t.me/c/1156511084/838

Astounding how clever some people are. Took me a bit of a while to really understand but in it's most basic form; Long ago neural networks and ML training was held linearly and consequently. Thanks to transformers ML algorithm can be trained in parallel. 🤯

It's basically like multi-threading but for neural nets.

#Papers #AttentionIsAllYouNeed
@Dagmawi_Babi

One nice teacher shared a ton (30+) of research papers across so many topics with me.

Enjoy
• https://t.me/c/1156511084/904

#Papers
@Dagmawi_Babi

Here's a very interesting paper I read this week

What happens if your CPU gets something wrong? If it wakes up one day and decides 2+2=5?

Well, most of us will never have to worry about that. But if you work at a company the size of Google, you do, which is why this paper on "mercurial cores" is so fascinating.

What the authors report--and supposedly this is common knowledge at the hyperscalers--is that a couple cores per several thousand machines are "mercurial." Due to subtle manufacturing defects or old age, they give wrong answers for certain instructions. These can cause all sorts of impossible-to-diagnose issues. Some rare problems at Google that were traced back to bad CPUs include:
• Mutexes not working, causing application crashes
• Silent data corruption
• Garbage collectors targeting live memory, causing application crashes
• Kernel state corruption causing kernel panics

What makes CPUs go bad? It's very hard to tell. The authors posit that issues are becoming more frequent as CPUs get more complex, but there aren't solid numbers behind that. There are certainly strong relationships between frequency, temperature, voltage, and bad CPU behavior--most mercurial CPUs only cause problems under very specific conditions, but those conditions vary from CPU to CPU. Age is another source of problems, as older CPUs are more likely to exhibit problems.

Bad CPUs are an especially serious problem because they're very hard to detect. If cosmic rays flip bits in storage or on the network, that can be detected through error coding. But there's no analogy for a CPU that allows cheap online verification of its correctness. Instead, the best detection techniques involve monitoring for symptoms. If a core exhibits exceptionally high rates of process crashes or kernel panics relative to its fellows, that's a strong indication something is wrong with it. For the most critical applications, the authors propose triple modular redundancy--redoing each of its computations on three cores and majority-voting a reliable result.

#Papers #CoresThatDontCount
@Dagmawi_Babi

100 LLM Papers to explore

This curated collection comprises 100 papers that delve into the world of Large Language Models (LLMs). If you're an enthusiast, researcher, or simply someone looking to explore developments in the field of language models, this dataset is a treasure trove.

The papers in this dataset cover a wide range of topics within the LLM domain, from the foundational Transformer architectures to advanced techniques in model compression, activation functions, pruning, quantization, normalization, sparsity, fine-tuning, sampling, scaling, mixture of experts, watermarking, and much more.

#Papers #LLMs
@Dagmawi_Babi

Highly accurate protein structure prediction with AlphaFold. AlphaFold is obviously very impressive.

#Papers
@Dagmawi_Babi

Turns out people tip more to women who are young, got big boobs, whose hair is dyed (or blonde) and are thinner.

And if you're older, smaller boobs, hair is normal (or not blonde) and if you're fatter you get tipped less.

No surprise that attractiveness does play a big role in the waitressing industry. Found it from this research paper done in 2008.

#Papers
@Dagmawi_Babi