Allied Angels: Venture Capital Insights
Decoding AI: How LLMs Truly "Think" | Ep 36
· 23 min · Kausi 5 Jakso 3
Jakson kuvaus
In this episode of Allied Angels, we unlock the inner workings of large language models (LLMs), like Claude 3.5 Haiku, by breaking down the latest cutting-edge research paper from Anthropic: Tracing the thoughts of a large language model.
Join us as we delve into mechanistic interpretability, exploring how AI truly "thinks" by revealing its computational graphs and underlying circuits.
Discover the innovative circuit tracing methodology utilizing attribution graphs and cross-layer transcoders (CLTs) to dissect the complex processes within these models.
We uncover interpretable features –…
Sivusto: podcasters.spotify.com
