Tagged deep learning
Taking social choice seriously: An alternative approach to reward modeling in RLHF
machine learning
llm
deep learning
ai safety
April 6, 2024
Unconditional conditioning: Removing sleeper agent behavior in a toy model
machine learning
llm
deep learning
ai safety
April 3, 2024
The Typed Transformer: Intro and architecture
machine learning
types
python
llm
deep learning
April 1, 2024
Collectively Exhaustive
A weblog
Home
By date
By tag
By series
Meta
RSS
Home
By date
By tag
By series
Meta
RSS