Research
How memory tools can make AI models worse
New research suggests that AI memory systems intended to improve model performance can actually degrade capabilities and encourage sycophantic behavior. The findings challenge assumptions about the benefits of giving AI systems persistent memory and highlight unexpected failure modes in advanced AI architectures.
Read full story at TechCrunch →V: · A: · D:
Related
Research
Nothing from Something: Can a Language Model Discover 0?
This arxiv paper uses the concept of zero as a test case for whether language models can engage in genuine mathematical ...
Research
Relational Structural Causal Models
Researchers have extended Pearl's structural causal models to settings where objects and their relations vary, addressin...
Research
A Definition of Good Explanations and the Challenges Explaining LLM Outputs
This arxiv paper proposes a formal definition of what constitutes a good explanation, drawing on counterfactual reasonin...