Posts
-
Frontier AI Models Still Fail at Basic Physical Tasks: A Manufacturing Case Study
-
Using an LLM perplexity filter to detect weight exfiltration
-
Evaluating Sparse Autoencoders with Board Games
-
An Intuitive Explanation of Sparse Autoencoders for LLM Interpretability
-
Manipulating Chess-GPT's World Model
-
Chess-GPT's Internal World Model
subscribe via RSS