Julia Turc

machine learning

artificial intelligence

language models

AI explainer videos from a former Google Research engineer, now startup founder. Expect American optimism with a solid dose of Eastern European cynicism.

Find (free) supplemental materials (slide decks, paper reading lists, Colab notebooks) on Patreon 👉 https://www.patreon.com/c/JuliaTurc

The myth of 1-bit LLMs | Extreme Quantization

The myth of 1-bit LLMs | Extreme Quantization
Quantization: How LLMs survive in low precision

Quantization: How LLMs survive in low precision
Knowledge Distillation: How LLMs train each other

Knowledge Distillation: How LLMs train each other
Mixture of Experts: How LLMs get bigger without getting slower

Mixture of Experts: How LLMs get bigger without getting slower
Llama 4 Explained: Architecture, Long Context, and Native Multimodality

Llama 4 Explained: Architecture, Long Context, and Native Multimodality
DeepSeek's GRPO (Group Relative Policy Optimization) | Reinforcement Learning for LLMs

DeepSeek's GRPO (Group Relative Policy Optimization) | Reinforcement Learning for LLMs
Proximal Policy Optimization (PPO) for LLMs Explained Intuitively

Proximal Policy Optimization (PPO) for LLMs Explained Intuitively
Tülu 3 from AI2: Full open-source fine-tuning recipe for LLMs

Tülu 3 from AI2: Full open-source fine-tuning recipe for LLMs
8 Timeless tips for training LLMs | Become a better ML engineer

8 Timeless tips for training LLMs | Become a better ML engineer
How does OpenAI Operator work under the hood? | Tech deep dive

How does OpenAI Operator work under the hood? | Tech deep dive
How does DeepSeek actually work? | Full technical review

How does DeepSeek actually work? | Full technical review
Discover How LLMs Work by Dissecting Llama

Discover How LLMs Work by Dissecting Llama