12 years of studying foreign languages with Anki
28 December 2024
12 years of studying foreign languages with Anki
Blogposts
Data science, career and other topics
Browse by category:
Paper Review: Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
23 December 2024
BERT rebuilt with modern tricks — 2 trillion training tokens, 8192 context length, Flash Attention, and rotary embeddings — delivering state-of-the-art classification and retrieval with the best speed/memory efficiency among encoders.
Paper Review: Byte Latent Transformer: Patches Scale Better Than Tokens
16 December 2024
My review of the paper Byte Latent Transformer Patches Scale Better Than Tokens
Paper Review: Reverse Thinking Makes LLMs Stronger Reasoners
09 December 2024
My review of the paper Reverse Thinking Makes LLMs Stronger Reasoners
Paper Review: Project Sid: Many-agent simulations toward AI civilization
25 November 2024
What happens when you put 1k AI agents in Minecraft and let them self-organize? They form governments, transmit culture, develop religions, and build legal systems.
Paper Review: Large Language Models Orchestrating Structured Reasoning Achieve Kaggle Grandmaster Level
11 November 2024
My review of the paper Large Language Models Orchestrating Structured Reasoning Achieve Kaggle Grandmaster Level