Anthropic can now track the bizarre inner workings of a large language model
Will Douglas Heaventechnologyreview.com
Saved by Joe Gerber and
Anthropic can now track the bizarre inner workings of a large language model
We knew very little about how LLMs actually work...until now.
@AnthropicAI just dropped the most insane research paper, detailing some of the ways AI "thinks."
And it's completely different than we thought.
Here are their wild findings: 🧵 https://t.co/S8sar0Rn0M
On the Biology of a Large Language Model
transformer-circuits.pub
Remarkably, with a vast number of adjustable parameters (called weights), LLMs can create a model that emulates how humans communicate through written text.