Search Results for author:
Found 6 papers, 0 papers with code
Imitating Interactive Intelligence
These evaluations convincingly demonstrate that interactive training and auxiliary losses improve agent behaviour beyond what is achieved by supervised learning of actions alone.
Safe Deep RL in 3D Environments using Human Feedback
In this paper we answer this question in the affirmative, using ReQueST to train an agent to perform a 3D first-person object collection task using data entirely from human contractors.
Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals
However, an AI system may pursue an undesired goal even when the specification is correct, in the case of goal misgeneralization.
Explaining grokking through circuit efficiency
One of the most surprising puzzles in neural network generalisation is grokking: a network with perfect training accuracy but poor generalisation will, upon further training, transition to perfect generalisation.
Challenges with unsupervised LLM knowledge discovery
We show that existing unsupervised methods on large language model (LLM) activations do not discover knowledge -- instead they seem to discover whatever feature of the activations is most prominent.
Improving Dictionary Learning with Gated Sparse Autoencoders
Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by finding sparse, linear reconstructions of LM activations.
