Offshore
Photo
Ahmad
there's always a karpathy tweet for everything https://t.co/XaWCHaKzT7
tweet
Offshore
Photo
Ahmad
seeing cs students grinding this stuff is a W

oxycblt is gmi

from-scratch transformer update: i may not be modeling language yet but here's some pretty convolutional filters

im still predicting digits but the convolutions i set up should enable me to implement gated convnets for language modeling. while these were obsoleted by the transformer i still want to implement them to compare how they learn language versus attention

it also turns out while implementing convnets that my tensor was still ridiculously slow. with the addition of stride arithmetic and batch parallelism i was able to reduce my training time by 80x from 2 hours/epoch to 1.5 mins/epoch

my next step is quickly implementing a simpler language model (bengio) just to set up learnable embeddings, and then ill finally be able to start making real language models
- oxycblt
tweet
Offshore
Photo
Ahmad
RT @TheAhmadOsman: i woke up this morning with one thought on my mind

> Costco for GPUs https://t.co/BgRrgfwjuX
tweet
Offshore
Photo
Yellowbrick Investing
$VIRT

Bought $VIRT today for ~$33.80. Stock -26% in 3 months due to CEO retirement & low EPS estimate for 3Q. Trading at P/E of 7x (mgmt defin.) which is too cheap. I think market is wrong and $VIRT has a few near-term catalysts that'll lead to re-rating. Thread (1/n) 🧵 https://t.co/nLmFFDJoKC
- secretlyaninja
tweet
Ahmad
the top 10 most influential LLM releases that defined opensource AI

> BERT

> GPT-2

> LLaMA 1

> Alpaca

> LLaMA 2

> Mistral 7B

> Mixtral 8×7B

> LLaMA 3

> Qwen 2.5

> DeepSeek R1
tweet
Offshore
Photo
Read
RT @MebFaber: One of my favorite reads of the year...

"...by far the most powerful predictor of long-term equity performance is the starting P/E or CAPE ratio."

@DeutscheBank via @TheIdeaFarm https://t.co/hQncpmbd9l
tweet
Offshore
Video
Ahmad
RT @sadernoheart: https://t.co/Ck1AOx38oM

didnt even touch outside the terminal, claude did everything from implementation to pushing the code to github to writing the readme https://t.co/RrOU2HVIhe
- sadernoheart
tweet
Ahmad
RT @TheAhmadOsman: @0xIlyy at this point if you're still in CS you're doing it for the love of the game
tweet
Offshore
Photo
Read
RT @F_Compounders: Understanding ROE

Picking stocks The Buffett Way https://t.co/DviW4MJy4a
tweet