x

LESSWRONG

LW

Agastya Agrawal

Agastya Agrawal

Message

https://agastyaagrawal.github.io/

44

2

1

5mo

Agastya Agrawal

https://agastyaagrawal.github.io/

Agastya Agrawal — LessWrong

Singular Learning Theory Comprehensive - 1

Introduction There are some very nice resources to understand the intuition of Singular Learning Theory. However, I am quite unsatisfied with the current resources online explaining or approaching the subject, as I find them quite concise and brief - skipping many concepts that actually serve to strengthen the intuition to...

Uncovering Unfaithful CoT in Deceptive Models

Inspired by the paper Modifying LLM Beliefs with Synthetic Document Finetuning, I fine-tuned an AI model to adopt the personality of a detective and generate unfaithful Chain-Of-Thought (CoT) in order to conceal their true investigative intent, and be able to solve mystery cases. The project primarily investigates two questions: 1....