Generalizability in LLM-ology, revisited - by Sean Trott
What does it mean to say two circuits in two different models "do the same thing"?| seantrott.substack.com
What does it mean to say two circuits in two different models "do the same thing"?| seantrott.substack.com
How can a science of LLMs keep up with technological development?| seantrott.substack.com
Three hard questions for a new paradigm.| seantrott.substack.com
Do we need a CERN for LLM-ology?| seantrott.substack.com
How to get started studying LLMs.| seantrott.substack.com
Stochastic parrots, blurry JPEGs, aliens, and more.| seantrott.substack.com
Trying to peek inside the "black box".| seantrott.substack.com
Measuring what you want to measure is hard.| seantrott.substack.com
Want to really understand how large language models work? Here’s a gentle primer.| www.understandingai.org
