HN user

silasalberti

7 karma

Building Cognition, prev: AI PhD @ stanford, Google DeepMind, Jane Street

Twitter: x.com/silasalberti Website: sil.as

Posts3
Comments5
View on HN

When working with LLMs you can never exclude hallucinations entirely but we‘ve been carefully tuning the system over time and found it to be pretty high signal! The reason we display the code snippets is to make it easy to double check with the source