The limits of our language-based benchmarks are the limits of our language.| seantrott.substack.com
Knowledge distillation happens in many forms.| seantrott.substack.com
Exploring the new multimodal model from AI2.| seantrott.substack.com
How do VLMs combine their modalities?| seantrott.substack.com
Cognitive architectures, extended minds, and distributed cognition.| seantrott.substack.com
How to get started studying LLMs.| seantrott.substack.com
The sociolinguistics of large language models.| seantrott.substack.com
Trying to peek inside the "black box".| seantrott.substack.com
Modern language models predict "tokens", not words—but what exactly are tokens?| seantrott.substack.com