A mind-expanding conversation on how models actually work | Emmanuel Ameisen (Anthropic)
Long-form conversation with Anthropic's Emmanuel Ameisen on how models actually work; deep, builder-relevant interpretability content.
More in Models
34:33ModelsScience Behind the Open Cyber Frontier with Mistral Large 4
Mistralopen weights
Hugging Face
21:12ModelsDeepseek crushed everyone
DeepSeekopen weights
47:58ModelsPost-Training Nemotron for Europe | Nemotron Labs
Nemotronpost-training
NVIDIA
